{
  "schema_version": 1,
  "server_id": "haymon-dbmcp",
  "package": "@haymon-ai/dbmcp",
  "version": "0.18.0",
  "collected_at": "2026-11-16T23:35:35.843Z",
  "analyzed_at": "2026-11-16T23:35:35.843Z",
  "modelara_version": "v0.1.8",
  "fingerprint": "sha256:ae96c237c8532ff448f4aad9f6de5b02b43c294a3b91eaa67ec029771b4a6803",
  "tool_count": 8,
  "interface": {
    "format": "modelara.inspect/v0",
    "capability_set": {
      "source": {
        "type": "mcp",
        "name": "dbmcp",
        "title": "Database MCP Server",
        "version": "0.18.0",
        "protocol_version": "2025-11-25"
      },
      "discovered_at": "2026-11-16T23:35:35.642868329Z",
      "capabilities": [
        {
          "id": "mcp:dbmcp/explainQuery",
          "name": "explainQuery",
          "title": "Explain Query",
          "description": "Return the execution plan for a SQL query to diagnose performance. Use this tool instead of running EXPLAIN directly through readQuery — it provides structured output.\n\n<usecase>\nUse when:\n- A query runs slowly and you need to understand why\n- Investigating performance bottlenecks\n- Planning index creation to optimize queries\n- Analyzing join methods, table scan strategies, and sort operations\n</usecase>\n\n<when_not_to_use>\n- Running actual queries → use readQuery, or writeQuery for data changes (not available in read-only mode)\n- Checking table structure → use listTables(detailed=true)\n</when_not_to_use>\n\n<examples>\n✓ \"Why is my SELECT on orders slow?\" → explainQuery(query=\"SELECT ...\")\n✓ \"Should I add an index?\" → explainQuery with analyze=true\n✗ \"Run this SELECT\" → use readQuery\n</examples>\n\n<safety>\nSet `analyze` to true for actual execution statistics (EXPLAIN ANALYZE).\nIMPORTANT: EXPLAIN ANALYZE actually executes the query! In read-only mode, only read-only statements are allowed with analyze.\nWhen analyze is false, returns EXPLAIN FORMAT=JSON output without executing.\nOnly a single SQL statement is accepted.\n</safety>\n\n<what_it_returns>\nA JSON array of execution plan rows showing access methods, join types, row estimates, and costs.\n\nLong string values are cut and end in `…[truncated, N chars total]`, and rows past the response size cap are dropped and counted in `rowsOmitted`; when either happens the response carries `truncated: true` and a `hint`.\n</what_it_returns>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "explainQuery"
          },
          "input_schema": {
            "properties": {
              "analyze": {
                "default": false,
                "description": "If true, use EXPLAIN ANALYZE for actual execution statistics. In read-only mode, only allowed for read-only statements. Defaults to false.",
                "type": "boolean"
              },
              "database": {
                "default": null,
                "description": "Database to explain against. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "query": {
                "description": "The SQL query to explain.",
                "type": "string"
              }
            },
            "required": [
              "query"
            ],
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "hint": {
                "description": "How to fetch less data; present only when `truncated` is `true`.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "rows": {
                "description": "Result rows, each a JSON object keyed by a column name.",
                "items": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "type": "array"
              },
              "rowsOmitted": {
                "description": "Rows the response cap dropped that no cursor can fetch again.",
                "format": "uint64",
                "minimum": 0,
                "type": [
                  "integer",
                  "null"
                ]
              },
              "truncated": {
                "description": "Present and `true` when a character cap cut a value or dropped rows.",
                "type": "boolean"
              }
            },
            "required": [
              "rows"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "true"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "true"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:f586a8c1478429a1ab99e6986db6e90f8fba9e0a7bf05434dce7abd3c3764f64"
        },
        {
          "id": "mcp:dbmcp/listDatabases",
          "name": "listDatabases",
          "title": "List Databases",
          "description": "List all accessible databases on the connected server. Use this tool to discover what databases are available before using other tools.\n\n<usecase>\nALWAYS call this tool FIRST when:\n- You need to explore what databases exist on the server\n- You need a database name for listTables or query tools\n- The user asks what data is available\n</usecase>\n\n<examples>\n✓ \"What databases are on this server?\"\n✓ \"Show me what's available\" → call listDatabases first\n</examples>\n\n<what_it_returns>\nA sorted JSON array of database name strings.\n</what_it_returns>\n\n<pagination>\nPaginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page.\n</pagination>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "listDatabases"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              }
            },
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "databases": {
                "description": "Sorted list of database names for this page.",
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final page.",
                "type": "string"
              }
            },
            "required": [
              "databases"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "false"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "false"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:0ea60ca9d00449bede163bd3b02dcbd365bcf2485dd85b307c34cb651463e2d8"
        },
        {
          "id": "mcp:dbmcp/listFunctions",
          "name": "listFunctions",
          "title": "List Functions",
          "description": "List user-defined SQL functions in a database, optionally filtered and/or with full metadata. Loadable UDFs (`mysql.func`) and stored procedures are excluded.\n\n<usecase>\nUse when:\n- Auditing stored functions across a database (brief mode, default).\n- Searching for a function by partial name (pass `search`).\n- Inspecting a function's language, signature, return type, determinism, SQL-data-access classification, security mode, definer, comment, session context, and full reconstructed `CREATE FUNCTION` text before reasoning about correctness or invocation safety (pass `detailed: true`). Detailed mode supersedes ad-hoc `readQuery` against `information_schema.ROUTINES` / `information_schema.PARAMETERS`.\n</usecase>\n\n<parameters>\n- `database` — Database to target. Defaults to the active database.\n- `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`.\n- `search` — Case-insensitive filter on function names via `LIKE`. `%` matches any sequence; `_` matches a single character.\n- `detailed` — When `true`, returns full metadata objects keyed by function name instead of bare name strings. Default `false`.\n</parameters>\n\n<examples>\n✓ \"What functions are in the mydb database?\" → listFunctions(database=\"mydb\")\n✓ \"Find the order-total calculation\" → listFunctions(search=\"order\")\n✓ \"What does calc_order_total do?\" → listFunctions(search=\"calc_order_total\", detailed=true)\n✗ \"List stored procedures\" → use listProcedures instead\n✗ \"List loadable UDFs from mysql.func\" → not supported; only routines in information_schema.ROUTINES are returned\n</examples>\n\n<what_it_returns>\nBrief mode (default): a sorted JSON array of function-name strings, e.g. `[\"calc_order_subtotal\", \"calc_order_total\", \"double_it\"]`.\nDetailed mode: a JSON object keyed by bare function name (MySQL/MariaDB do not allow function overloading, so no signature suffix is needed); each value carries `schema`, `language` (typically `\"SQL\"`; MariaDB external-language functions report the external language name), `arguments` (comma-separated `name type` pairs from `information_schema.PARAMETERS`, empty string for zero-parameter functions), `returnType` (full `DTD_IDENTIFIER` including length/precision/unsigned/enum/set members), `deterministic` (boolean), `sqlDataAccess` (one of `CONTAINS_SQL`, `NO_SQL`, `READS_SQL_DATA`, `MODIFIES_SQL_DATA`), `security` (`INVOKER` or `DEFINER`), `definer` (`user@host`), `description` (the `COMMENT` text or `null` when no comment was set — the empty string MySQL stores is coerced to JSON `null`), `definition` (the canonical reconstructed `CREATE FUNCTION` text including `DEFINER=` in `` `user`@`host` `` form), `sqlMode`, `characterSetClient`, `collationConnection`, and `databaseCollation`. Versus the Postgres detailed payload: `volatility`, `parallelSafety`, and `strict` are intentionally absent (no MySQL/MariaDB analogues), `owner` is renamed to `definer` (more accurate for the MySQL `DEFINER` concept), keys are bare names rather than `name(arguments)` (no overloads possible), and the four session-context fields (`sqlMode`, `characterSetClient`, `collationConnection`, `databaseCollation`) are MySQL/MariaDB-only additions.\n</what_it_returns>\n\n<pagination>\nPaginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. The `search` filter must stay the same across pages for cursor continuity.\n</pagination>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "listFunctions"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "database": {
                "default": null,
                "description": "Database to list functions from. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "detailed": {
                "default": false,
                "description": "When `true`, each returned entry is a full metadata object (schema, language,\narguments, returnType, deterministic, sqlDataAccess, security, definer,\ndescription, definition, sqlMode, characterSetClient, collationConnection,\ndatabaseCollation); when `false` or omitted, each entry is the bare\nfunction-name string.",
                "type": "boolean"
              },
              "search": {
                "default": null,
                "description": "Optional case-insensitive filter on function names. The input is used within a `LIKE`\nclause: `%` matches any sequence of characters and `_` matches any single character.",
                "type": [
                  "string",
                  "null"
                ]
              }
            },
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "entries": {
                "anyOf": [
                  {
                    "description": "Brief mode: sorted array of bare entity-name strings.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  {
                    "additionalProperties": true,
                    "description": "Detailed mode: name-keyed map; insertion order matches the SQL `ORDER BY` sort.",
                    "type": "object"
                  }
                ],
                "description": "Page of matching entries. Shape depends on the request's `detailed` flag."
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final page.",
                "type": "string"
              }
            },
            "required": [
              "entries"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "false"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "false"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:77c5501415017eb6a9f56c7dae0759f89fe37bb431686e8aaefc6ce05d7c554c"
        },
        {
          "id": "mcp:dbmcp/listProcedures",
          "name": "listProcedures",
          "title": "List Procedures",
          "description": "List user-defined stored procedures in a database, optionally filtered and/or with full metadata. Stored functions and loadable UDFs (`mysql.func`) are excluded.\n\n<usecase>\nUse when:\n- Auditing stored procedures across a database (brief mode, default).\n- Searching for a procedure by partial name (pass `search`).\n- Inspecting a procedure's language, parameter list (with `IN`/`OUT`/`INOUT` modes), determinism, SQL-data-access classification, security mode, definer, comment, session context, and full reconstructed `CREATE PROCEDURE` text before reasoning about correctness or invocation safety (pass `detailed: true`). Detailed mode supersedes ad-hoc `readQuery` against `information_schema.ROUTINES` / `information_schema.PARAMETERS`.\n</usecase>\n\n<parameters>\n- `database` — Database to target. Defaults to the active database.\n- `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`.\n- `search` — Case-insensitive filter on procedure names via `LIKE`. `%` matches any sequence; `_` matches a single character.\n- `detailed` — When `true`, returns full metadata objects keyed by procedure name instead of bare name strings. Default `false`.\n</parameters>\n\n<examples>\n✓ \"What procedures are in the mydb database?\" → listProcedures(database=\"mydb\")\n✓ \"Find the order archival routine\" → listProcedures(search=\"archive\")\n✓ \"What does archive_order do?\" → listProcedures(search=\"archive_order\", detailed=true)\n✗ \"List functions\" → use listFunctions instead\n✗ \"List loadable UDFs from mysql.func\" → not supported; only routines in information_schema.ROUTINES are returned\n</examples>\n\n<what_it_returns>\nBrief mode (default): a sorted JSON array of procedure-name strings, e.g. `[\"archive_order\", \"archive_order_history\", \"purge_order_archive\", \"touch_post\"]`.\nDetailed mode: a JSON object keyed by bare procedure name (MySQL/MariaDB do not allow procedure overloading, so no signature suffix is needed); each value carries `schema`, `language` (typically `\"SQL\"`; MariaDB external-language procedures report the external language name), `arguments` (comma-separated `MODE name type` triples from `information_schema.PARAMETERS` — `MODE` is one of `IN`, `OUT`, `INOUT`; empty string for zero-parameter procedures), `deterministic` (boolean), `sqlDataAccess` (one of `CONTAINS_SQL`, `NO_SQL`, `READS_SQL_DATA`, `MODIFIES_SQL_DATA`), `security` (`INVOKER` or `DEFINER`), `definer` (`user@host`), `description` (the `COMMENT` text or `null` when no comment was set — the empty string MySQL stores is coerced to JSON `null`), `definition` (the canonical reconstructed `CREATE PROCEDURE` text including `DEFINER=` in `` `user`@`host` `` form; no `RETURNS` clause — procedures have no return type), `sqlMode`, `characterSetClient`, `collationConnection`, and `databaseCollation`. Versus the Postgres `listProcedures` detailed payload: `volatility`, `parallelSafety`, `strict`, and `returnType` are intentionally absent (no MySQL/MariaDB analogues for the first three; procedures have no return type for the fourth — the Postgres-side payload also omits all four), `owner` is renamed to `definer` (more accurate for the MySQL `DEFINER` concept), keys are bare names rather than `name(arguments)` (no overloads possible), the four session-context fields (`sqlMode`, `characterSetClient`, `collationConnection`, `databaseCollation`) are MySQL/MariaDB-only additions, and `deterministic` plus `sqlDataAccess` are MySQL/MariaDB-only additions versus the Postgres `listProcedures` detailed payload (which omits both because Postgres procedures have no equivalent attributes).\n</what_it_returns>\n\n<pagination>\nPaginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. The `search` filter must stay the same across pages for cursor continuity.\n</pagination>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "listProcedures"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "database": {
                "default": null,
                "description": "Database to list procedures from. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "detailed": {
                "default": false,
                "description": "When `true`, each returned entry is a full metadata object (schema, language,\narguments with IN/OUT/INOUT mode tokens, deterministic, sqlDataAccess, security,\ndefiner, description, definition, sqlMode, characterSetClient,\ncollationConnection, databaseCollation); when `false` or omitted, each entry\nis the bare procedure-name string.",
                "type": "boolean"
              },
              "search": {
                "default": null,
                "description": "Optional case-insensitive filter on procedure names. The input is used within a `LIKE`\nclause: `%` matches any sequence of characters and `_` matches any single character.",
                "type": [
                  "string",
                  "null"
                ]
              }
            },
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "entries": {
                "anyOf": [
                  {
                    "description": "Brief mode: sorted array of bare entity-name strings.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  {
                    "additionalProperties": true,
                    "description": "Detailed mode: name-keyed map; insertion order matches the SQL `ORDER BY` sort.",
                    "type": "object"
                  }
                ],
                "description": "Page of matching entries. Shape depends on the request's `detailed` flag."
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final page.",
                "type": "string"
              }
            },
            "required": [
              "entries"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "false"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "false"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:985fbbb18f72aba567651f71547b138b4dda482c5741381f79fb544362d3d6c1"
        },
        {
          "id": "mcp:dbmcp/listTables",
          "name": "listTables",
          "title": "List Tables",
          "description": "List tables in a database, optionally filtered and/or with full metadata.\n\n<usecase>\nUse when:\n- Exploring a database to find relevant tables (brief mode, default).\n- Searching for a table by partial name (pass `search`).\n- Inspecting a table's columns, constraints, indexes, and triggers before writing a query (pass `detailed: true`).\n</usecase>\n\n<parameters>\n- `database` — Database to target. Defaults to the active database.\n- `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`.\n- `search` — Case-insensitive filter on table names via `LIKE`. `%` matches any sequence; `_` matches a single character.\n- `detailed` — When `true`, returns full metadata objects keyed by table name instead of bare name strings. Default `false`.\n</parameters>\n\n<examples>\n✓ \"What tables are in mydb?\" → listTables(database=\"mydb\")\n✓ \"Find the orders table\" → listTables(search=\"order\")\n✓ \"What columns does orders have?\" → listTables(search=\"orders\", detailed=true)\n</examples>\n\n<what_it_returns>\nBrief mode (default): a sorted JSON array of table-name strings, e.g. `[\"customers\", \"orders\"]`.\nDetailed mode: a JSON object keyed by table name; each value carries `schema`, `kind`, `owner`, `comment`, `columns`, `constraints`, `indexes`, and `triggers` (the name is the key and is not repeated inside the value). Keys iterate in the same alphabetical order brief mode uses. Example: `{\"orders\": {\"schema\": \"mydb\", \"kind\": \"TABLE\", …}}`.\n</what_it_returns>\n\n<pagination>\nPaginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. The `search` filter must stay the same across pages for cursor continuity.\n</pagination>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "listTables"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "database": {
                "default": null,
                "description": "Database to list tables from. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "detailed": {
                "default": false,
                "description": "When `true`, each returned entry is a full metadata object (columns,\nconstraints, indexes, triggers, owner, comment, kind); when `false` or\nomitted, each entry is the bare table-name string.",
                "type": "boolean"
              },
              "search": {
                "default": null,
                "description": "Optional case-insensitive filter on table names. The input is used within a `LIKE`\nclause: `%` matches any sequence of characters and `_` matches any single character.",
                "type": [
                  "string",
                  "null"
                ]
              }
            },
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "entries": {
                "anyOf": [
                  {
                    "description": "Brief mode: sorted array of bare entity-name strings.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  {
                    "additionalProperties": true,
                    "description": "Detailed mode: name-keyed map; insertion order matches the SQL `ORDER BY` sort.",
                    "type": "object"
                  }
                ],
                "description": "Page of matching entries. Shape depends on the request's `detailed` flag."
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final page.",
                "type": "string"
              }
            },
            "required": [
              "entries"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "false"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "false"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:a0ed3b844f3d97523c937bf3d1e4b8c87bf2d9536840d065790402fb613e5b20"
        },
        {
          "id": "mcp:dbmcp/listTriggers",
          "name": "listTriggers",
          "title": "List Triggers",
          "description": "List user-defined triggers in a database, optionally filtered and/or with full metadata.\n\n<usecase>\nUse when:\n- Auditing trigger coverage across a database (brief mode, default).\n- Searching for a trigger by partial name (pass `search`).\n- Inspecting a trigger's timing, event, activation level, full `CREATE TRIGGER` text, and the session context active at trigger-creation time before reasoning about side-effects (pass `detailed: true`). Detailed mode supersedes ad-hoc `readQuery` against `information_schema.TRIGGERS`.\n</usecase>\n\n<parameters>\n- `database` — Database to target. Defaults to the active database.\n- `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`.\n- `search` — Case-insensitive filter on trigger names via `LIKE`. `%` matches any sequence; `_` matches a single character.\n- `detailed` — When `true`, returns full metadata objects keyed by trigger name instead of bare name strings. Default `false`.\n</parameters>\n\n<examples>\n✓ \"What triggers are in the mydb database?\" → listTriggers(database=\"mydb\")\n✓ \"Find the audit triggers\" → listTriggers(search=\"audit\")\n✓ \"What does orders_audit_after_insert do?\" → listTriggers(search=\"orders_audit_after_insert\", detailed=true)\n✗ \"Show me a trigger's body\" → use detailed mode; the `definition` field carries the full `CREATE TRIGGER` text\n</examples>\n\n<what_it_returns>\nBrief mode (default): a sorted JSON array of trigger-name strings, e.g. `[\"customers_audit_after_insert\", \"orders_audit_after_insert\"]`.\nDetailed mode: a JSON object keyed by trigger name; each value carries `schema`, `table`, `timing` (BEFORE/AFTER), `events` (single-element array — `INSERT`, `UPDATE`, or `DELETE`), `activationLevel` (always `ROW` on MySQL/MariaDB), `definition` (the canonical `CREATE TRIGGER` text including `DEFINER=` in `` `user`@`host` `` form), `sqlMode`, `characterSetClient`, `collationConnection`, and `databaseCollation`. The Postgres-only `status` and `functionName` fields are intentionally absent (no per-trigger enabled/disabled flag and no separate handler-function reference on MySQL/MariaDB); the four session-context fields are MySQL/MariaDB-only additions versus the Postgres detailed payload.\n</what_it_returns>\n\n<pagination>\nPaginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. The `search` filter must stay the same across pages for cursor continuity.\n</pagination>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "listTriggers"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "database": {
                "default": null,
                "description": "Database to list triggers from. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "detailed": {
                "default": false,
                "description": "When `true`, each returned entry is a full metadata object (schema, table, timing,\nevents, activationLevel, definition, plus backend-specific fields); when `false` or\nomitted, each entry is the bare trigger-name string.",
                "type": "boolean"
              },
              "search": {
                "default": null,
                "description": "Optional case-insensitive filter on trigger names. The input is used within a `LIKE`\nclause: `%` matches any sequence of characters and `_` matches any single character.",
                "type": [
                  "string",
                  "null"
                ]
              }
            },
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "entries": {
                "anyOf": [
                  {
                    "description": "Brief mode: sorted array of bare entity-name strings.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  {
                    "additionalProperties": true,
                    "description": "Detailed mode: name-keyed map; insertion order matches the SQL `ORDER BY` sort.",
                    "type": "object"
                  }
                ],
                "description": "Page of matching entries. Shape depends on the request's `detailed` flag."
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final page.",
                "type": "string"
              }
            },
            "required": [
              "entries"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "false"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "false"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:372c5b6219021eea7702a8c93c93f768da214d3ffd2c950480e113e464c647cc"
        },
        {
          "id": "mcp:dbmcp/listViews",
          "name": "listViews",
          "title": "List Views",
          "description": "List user-defined views in a database, optionally filtered and/or with full metadata. Base tables and system-schema views are excluded.\n\n<usecase>\nUse when:\n- Auditing views across a database (brief mode, default).\n- Searching for a view by partial name (pass `search`).\n- Inspecting a view's definer, security mode, check-option level, updatable flag, session character set/collation, and full SELECT body before querying it (pass `detailed: true`). Detailed mode supersedes ad-hoc `readQuery` against `information_schema.VIEWS`.\n</usecase>\n\n<parameters>\n- `database` — Database to target. Defaults to the active database.\n- `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`.\n- `search` — Case-insensitive filter on view names via `LIKE`. `%` matches any sequence; `_` matches a single character.\n- `detailed` — When `true`, returns full metadata objects keyed by view name instead of bare name strings. Default `false`.\n</parameters>\n\n<examples>\n✓ \"What views are in the mydb database?\" → listViews(database=\"mydb\")\n✓ \"Find the active-users view\" → listViews(search=\"active\")\n✓ \"What does active_users select?\" → listViews(search=\"active_users\", detailed=true)\n✗ \"Show me the columns of a view\" → use listTables with `detailed: true` instead\n✗ \"List materialized views\" → MySQL/MariaDB have no materialized-view concept\n</examples>\n\n<what_it_returns>\nBrief mode (default): a sorted JSON array of view-name strings, e.g. `[\"active_orders\", \"active_users\", \"published_posts\"]`.\nDetailed mode: a JSON object keyed by bare view name; each value carries `schema`, `definer` (`user@host`), `security` (`INVOKER` or `DEFINER`), `checkOption` (`NONE`, `CASCADED`, or `LOCAL`), `updatable` (boolean), `characterSetClient`, `collationConnection`, and `definition` (the SELECT body verbatim from `information_schema.VIEWS.VIEW_DEFINITION`, with no `CREATE VIEW` wrapper). The view name is the map key only — it is not repeated inside the value.\n\nVersus the Postgres `listViews` detailed payload: `description` is intentionally absent (neither MySQL nor MariaDB exposes a user-comment column for views — `CREATE VIEW` syntax has no `COMMENT` clause), `algorithm` is intentionally absent (MariaDB-only column on `information_schema.VIEWS`), `owner` is renamed to `definer` (more accurate for the MySQL `DEFINER` concept), and the five MySQL/MariaDB-only structured fields (`security`, `checkOption`, `updatable`, `characterSetClient`, `collationConnection`) are added. The `definition` field shape is byte-identical to Postgres — raw SELECT body verbatim, no DDL wrapper. When the connected role lacks the `SHOW VIEW` privilege on a particular view, the engine redacts `VIEW_DEFINITION` to the empty string; the row remains in the response with `definition` reflecting that empty value.\n</what_it_returns>\n\n<pagination>\nPaginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. The `search` filter must stay the same across pages for cursor continuity. Brief and detailed modes share the same `TABLE_NAME` row order, so a client can switch `detailed` between pages without losing position.\n</pagination>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "listViews"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "database": {
                "default": null,
                "description": "Database to list views from. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "detailed": {
                "default": false,
                "description": "When `true`, each returned entry is a full metadata object (schema, definer,\nsecurity, checkOption, updatable, characterSetClient, collationConnection,\ndefinition); when `false` or omitted, each entry is the bare view-name string.",
                "type": "boolean"
              },
              "search": {
                "default": null,
                "description": "Optional case-insensitive filter on view names. The input is used within a `LIKE`\nclause: `%` matches any sequence of characters and `_` matches any single character.",
                "type": [
                  "string",
                  "null"
                ]
              }
            },
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "entries": {
                "anyOf": [
                  {
                    "description": "Brief mode: sorted array of bare entity-name strings.",
                    "items": {
                      "type": "string"
                    },
                    "type": "array"
                  },
                  {
                    "additionalProperties": true,
                    "description": "Detailed mode: name-keyed map; insertion order matches the SQL `ORDER BY` sort.",
                    "type": "object"
                  }
                ],
                "description": "Page of matching entries. Shape depends on the request's `detailed` flag."
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final page.",
                "type": "string"
              }
            },
            "required": [
              "entries"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "false"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "false"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:f6adb671b24a06bdc2769b6da44be8e3d12b4979dcc076bd40be82267bb382f6"
        },
        {
          "id": "mcp:dbmcp/readQuery",
          "name": "readQuery",
          "title": "Read Query",
          "description": "Execute a read-only SQL query. Allowed statements: SELECT, SHOW, DESCRIBE, EXPLAIN.\n\n<usecase>\nUse when:\n- Querying data from tables (SELECT with WHERE, JOIN, GROUP BY, etc.)\n- Aggregations: COUNT, SUM, AVG, GROUP BY, HAVING\n- Listing server variables or status (SHOW)\n- Viewing table structure (DESCRIBE)\n</usecase>\n\n<when_not_to_use>\n- Data changes (INSERT, UPDATE, DELETE) → use writeQuery (not available in read-only mode)\n- Query performance analysis → use explainQuery\n- Discovering tables or columns → use listTables (pass detailed=true for column-level metadata)\n- Switching database context (USE is rejected) → pass the `database` argument\n</when_not_to_use>\n\n<examples>\n✓ \"SELECT * FROM users WHERE status = 'active'\"\n✓ \"SELECT COUNT(*) FROM orders GROUP BY region\"\n✓ \"SHOW TABLES\" or \"DESCRIBE users\"\n✗ \"INSERT INTO users ...\" → use writeQuery (not available in read-only mode)\n✗ \"EXPLAIN SELECT ...\" → use explainQuery for structured analysis\n</examples>\n\n<what_it_returns>\nA JSON array of row objects, each keyed by column name.\n\nLong string values are cut and end in `…[truncated, N chars total]`; read the rest with `SUBSTRING`/`SUBSTR`. Rows past the response size cap are dropped: a `SELECT` page ends early and `nextCursor` resumes at the first row left out, while other statements report the count in `rowsOmitted`. When either happens the response carries `truncated: true` and a `hint`.\n</what_it_returns>\n\n<pagination>\n`SELECT` results are paginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. Order by a unique key so pages neither skip nor repeat rows. `SHOW`, `DESCRIBE`, and `EXPLAIN` return a single page and ignore `cursor`.\n</pagination>\n\n<timeout>\nEach call stops at the configured query timeout. On a timeout, check the plan with explainQuery before retrying: filter on indexed columns, or limit inner result sets before joining or aggregating. For a query known to be slow, pass `timeout` (seconds, at least 1) to allow more time. This only helps if the server allows a higher maximum, which is often the same as the default; a value above it is rejected with an error naming the maximum.\n</timeout>",
          "source": {
            "type": "mcp",
            "server": "dbmcp",
            "operation": "readQuery"
          },
          "input_schema": {
            "properties": {
              "cursor": {
                "default": null,
                "description": "Opaque cursor from a prior response's `nextCursor`; omit for the first page.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "database": {
                "default": null,
                "description": "Database to run the query against. Defaults to the active database.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "query": {
                "description": "The SQL query to execute.",
                "type": "string"
              },
              "timeout": {
                "default": null,
                "description": "Seconds this call may run, from 1 up to the server maximum. Defaults to the configured query timeout.",
                "format": "uint64",
                "minimum": 1,
                "type": [
                  "integer",
                  "null"
                ]
              }
            },
            "required": [
              "query"
            ],
            "type": "object"
          },
          "output_schema": {
            "properties": {
              "hint": {
                "description": "How to fetch less data; present only when `truncated` is `true`.",
                "type": [
                  "string",
                  "null"
                ]
              },
              "nextCursor": {
                "description": "Opaque cursor pointing to the next page. Absent when this is the final\npage, when the result fits in one page, or when the statement is a\nnon-`SELECT` kind that does not paginate (e.g. `SHOW`, `EXPLAIN`).",
                "type": "string"
              },
              "rows": {
                "description": "Result rows, each a JSON object keyed by a column name.",
                "items": {
                  "additionalProperties": true,
                  "type": "object"
                },
                "type": "array"
              },
              "rowsOmitted": {
                "description": "Rows the response cap dropped that no cursor can fetch again.",
                "format": "uint64",
                "minimum": 0,
                "type": [
                  "integer",
                  "null"
                ]
              },
              "truncated": {
                "description": "Present and `true` when a character cap cut a value or dropped rows.",
                "type": "boolean"
              }
            },
            "required": [
              "rows"
            ],
            "type": "object"
          },
          "declared": {
            "read_only": "true",
            "destructive": "false",
            "idempotent": "true",
            "open_world": "true"
          },
          "effects": {
            "kind": "read",
            "destructive": "false",
            "external": "true"
          },
          "safety": {
            "idempotent": "true",
            "retry_safe": "true"
          },
          "effect_assessment": {
            "kind": "read",
            "basis": "declared"
          },
          "metadata": {
            "mcp.annotations": "present"
          },
          "fingerprint": "sha256:3d86ccbcd98bc1d44802321c4589ce10c161bdd2a195eebdce053baebc68b257"
        }
      ],
      "discovery_order": [
        "mcp:dbmcp/explainQuery",
        "mcp:dbmcp/listDatabases",
        "mcp:dbmcp/listFunctions",
        "mcp:dbmcp/listProcedures",
        "mcp:dbmcp/listTables",
        "mcp:dbmcp/listTriggers",
        "mcp:dbmcp/listViews",
        "mcp:dbmcp/readQuery"
      ],
      "fingerprint": "sha256:ae96c237c8532ff448f4aad9f6de5b02b43c294a3b91eaa67ec029771b4a6803"
    },
    "summary": {
      "total": 8,
      "read_only": 8,
      "potential_writes": 0,
      "destructive": 0,
      "unknown_effects": 0,
      "retry_safe": 8
    },
    "schema_stats": {
      "mcp:dbmcp/explainQuery": {
        "input": {
          "properties": 3,
          "required": 1,
          "total_properties": 3,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 3
        },
        "output": {
          "properties": 4,
          "required": 1,
          "total_properties": 4,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 6
        }
      },
      "mcp:dbmcp/listDatabases": {
        "input": {
          "properties": 1,
          "required": 0,
          "total_properties": 1,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 1
        },
        "output": {
          "properties": 2,
          "required": 1,
          "total_properties": 2,
          "nested_objects": 0,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 3
        }
      },
      "mcp:dbmcp/listFunctions": {
        "input": {
          "properties": 4,
          "required": 0,
          "total_properties": 4,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 4
        },
        "output": {
          "properties": 2,
          "required": 1,
          "total_properties": 2,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 2,
          "refs": 0,
          "complexity": 6
        }
      },
      "mcp:dbmcp/listProcedures": {
        "input": {
          "properties": 4,
          "required": 0,
          "total_properties": 4,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 4
        },
        "output": {
          "properties": 2,
          "required": 1,
          "total_properties": 2,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 2,
          "refs": 0,
          "complexity": 6
        }
      },
      "mcp:dbmcp/listTables": {
        "input": {
          "properties": 4,
          "required": 0,
          "total_properties": 4,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 4
        },
        "output": {
          "properties": 2,
          "required": 1,
          "total_properties": 2,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 2,
          "refs": 0,
          "complexity": 6
        }
      },
      "mcp:dbmcp/listTriggers": {
        "input": {
          "properties": 4,
          "required": 0,
          "total_properties": 4,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 4
        },
        "output": {
          "properties": 2,
          "required": 1,
          "total_properties": 2,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 2,
          "refs": 0,
          "complexity": 6
        }
      },
      "mcp:dbmcp/listViews": {
        "input": {
          "properties": 4,
          "required": 0,
          "total_properties": 4,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 4
        },
        "output": {
          "properties": 2,
          "required": 1,
          "total_properties": 2,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 2,
          "refs": 0,
          "complexity": 6
        }
      },
      "mcp:dbmcp/readQuery": {
        "input": {
          "properties": 4,
          "required": 1,
          "total_properties": 4,
          "nested_objects": 0,
          "arrays": 0,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 4
        },
        "output": {
          "properties": 5,
          "required": 1,
          "total_properties": 5,
          "nested_objects": 1,
          "arrays": 1,
          "max_depth": 1,
          "combinators": 0,
          "refs": 0,
          "complexity": 7
        }
      }
    }
  },
  "source": {
    "registry": "npm",
    "package": "@haymon-ai/dbmcp",
    "version": "0.18.0",
    "published_at": "2026-11-11T17:04:55.076Z",
    "integrity": "sha512-ggIizQqFwoSyYAHbHENHwDNrxe6+LhKTtdI0675ZnWC1Iu5M+pmD6gNEDYcmaB5mUmgiu4bGV8N8lINHMTX3OQ==",
    "repository": "https://github.com/haymon-ai/dbmcp"
  },
  "analyzer": {
    "name": "modelara",
    "version": "v0.1.8",
    "policy_version": null
  },
  "capability_hash_version": 2,
  "capability_hashes": {
    "haymon-dbmcp:tool:explainQuery": {
      "description": "sha256:aabbdf19b29f2df38f6bfc77c0b5a2057d741144262e04091cca399f9cf11134",
      "input_schema": "sha256:5c9eb86638d08507fc748ae0ef45fbe07ac2564be6bdbd37b206836d37e7eaf3",
      "output_schema": "sha256:298fdeaf3ae9933a76cc3fd827a079284fc9bb757e550aa97a9f86022f2ad6d8",
      "interface": "sha256:374a9e60c924e753a0e9f497b32552b85d29d236a6ecc97359bc827019e153a5"
    },
    "haymon-dbmcp:tool:listDatabases": {
      "description": "sha256:9b7fe12b73399b4434d9fd4c393299aae71d23658776f0ff3a866abd5ce65c85",
      "input_schema": "sha256:9008030b75767a318fb9b2cb2cf444105f0337dcca92875cbaff72fd5a5a6519",
      "output_schema": "sha256:ad6956198d5e301b3f9bf1c312499230342cb08de1630e058660a920007193b7",
      "interface": "sha256:7fc16b74c38a3a0925aacd98cebc784534b5f313c4a81c7b94820d43fa8be906"
    },
    "haymon-dbmcp:tool:listFunctions": {
      "description": "sha256:2b685a6520066f05bb21414df3131100ea958fe955b27c28a652c308b5cb487f",
      "input_schema": "sha256:b7f37d65b2ddea36850898f7a44bf1c53cee967bdce9c15c3f42d33aa7e51277",
      "output_schema": "sha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27d",
      "interface": "sha256:cf07d8aeb992b7afd7183e593cf947a26504043f25c5e7818b12574d62878f8a"
    },
    "haymon-dbmcp:tool:listProcedures": {
      "description": "sha256:d724afa1a54d70da0a16966b1f78b8d86f874087f4a88a58460b9776ad7c2abd",
      "input_schema": "sha256:17b4d9b8bff89f3037a50a8b98bf26028031f26d77ab2136fa7603bc50c31b5e",
      "output_schema": "sha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27d",
      "interface": "sha256:cc6c76538d2b977547585a3eeb617b2dc4bed9534e8c3fa3cac654471b0e1b7a"
    },
    "haymon-dbmcp:tool:listTables": {
      "description": "sha256:b8877235ab71493fe576e60818c9c89d4d1b05ac17be5466ee91e84fd422e6c2",
      "input_schema": "sha256:9a7849de585a58c6c4a0aff6bcd893486c470afc0a7f45487d3ddcfcc29bfd33",
      "output_schema": "sha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27d",
      "interface": "sha256:8d061435c9a5d2f334b1cb7bf9b8b54d36f076afd0503d5b6219b1ea0861e291"
    },
    "haymon-dbmcp:tool:listTriggers": {
      "description": "sha256:9abd9cb8276a8c3b6f9922c2521162fe73b903224588f07b4f7fd55aba66fba6",
      "input_schema": "sha256:185159c7e34274bc598f91181da7b69b0fd4aee11a860e8dc2c96e070c543c72",
      "output_schema": "sha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27d",
      "interface": "sha256:1bf5e22363d6be26d92b305b489aac539d844b582346d789f8f6d6b57b27600a"
    },
    "haymon-dbmcp:tool:listViews": {
      "description": "sha256:af31be251e773ffa34ab06555e08c512a15f1edf0cbb6406861c2e7ec6a6c4d5",
      "input_schema": "sha256:00ca76677e1c81f69370ab241f849f579abc2d2f70831d1a33de1942390977eb",
      "output_schema": "sha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27d",
      "interface": "sha256:4444accca354968ccd5668a1138cbb2a09ce670f773236a423859673968825ed"
    },
    "haymon-dbmcp:tool:readQuery": {
      "description": "sha256:74ec15486b4ce0f5cad7c7ec15a19573f527c0f45687e57343697085a7fee907",
      "input_schema": "sha256:cd507ff6a3b1cbd852bcdba947b971fe4a3ad4ae70bcaf0caa67f3cd04cef204",
      "output_schema": "sha256:999feb2ae8d32aab91030cb9c6f1ffa7c18de6779187e5ddf2e4344c34e4d1de",
      "interface": "sha256:04fd982fef201c3ed7071cf900eb1b0d8cfa09e647ec5c0eb277b108c26e1711"
    }
  }
}
