Data MCP server
dbmcp
Version history of discovered tools, schemas, and declared agent authority.
OBSERVED INTERFACE
Capability surface
Modelara’s observed declarations are shown separately from its derived effect classifications.
- 8
- 0
- 0
- 0
Unknown means Valyd could not determine the capability's effect confidently from the declared interface and static evidence. It is not treated as safe.
- Package
- @haymon-ai/dbmcp@0.19.0
- Registry
- npm
- Published
- Nov 16, 2026
- Integrity
sha512-AElllCdpu2S3IAIi8eubbNMMov3+6XgNrHYwy3aEOpIKfMEl/HaTL3BXPux1tFxyWILon/wNf/Ceo1R5ciAX1Q==- Analyzer
- modelara v0.1.8 · policy not recorded
- Repository
- https://github.com/haymon-ai/dbmcp
8 capabilities
| Capability | Type | Derived effect | First observed in Valyd coverage | Last changed |
|---|---|---|---|---|
explainQueryhaymon-dbmcp:tool:explainQueryObserved interface and hashesReturn the execution plan for a SQL query to diagnose performance. Use this tool instead of running EXPLAIN directly through readQuery — it provides structured output. <usecase> Use when: - A query runs slowly and you need to understand why - Investigating performance bottlenecks - Planning index creation to optimize queries - Analyzing join methods, table scan strategies, and sort operations </usecase> <when_not_to_use> - Running actual queries → use readQuery, or writeQuery for data changes (not available in read-only mode) - Checking table structure → use listTables(detailed=true) </when_not_to_use> <examples> ✓ "Why is my SELECT on orders slow?" → explainQuery(query="SELECT ...") ✓ "Should I add an index?" → explainQuery with analyze=true ✗ "Run this SELECT" → use readQuery </examples> <safety> Set `analyze` to true for actual execution statistics (EXPLAIN ANALYZE). IMPORTANT: EXPLAIN ANALYZE actually executes the query, so only read-only statements are allowed with analyze. When analyze is false, returns EXPLAIN FORMAT=JSON output without executing. Write statements are rejected: the plan is fetched in a read-only transaction. Only a single SQL statement is accepted. </safety> <what_it_returns> A JSON array of execution plan rows showing access methods, join types, row estimates, and costs. Long 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`. </what_it_returns> Input schemasha256:5c9eb86638d08507fc748ae0ef45fbe07ac2564be6bdbd37b206836d37e7eaf3Output schemasha256:298fdeaf3ae9933a76cc3fd827a079284fc9bb757e550aa97a9f86022f2ad6d8Description hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | 0.19.0 | |
listDatabaseshaymon-dbmcp:tool:listDatabasesObserved interface and hashesList all accessible databases on the connected server. Use this tool to discover what databases are available before using other tools. <usecase> ALWAYS call this tool FIRST when: - You need to explore what databases exist on the server - You need a database name for listTables or query tools - The user asks what data is available </usecase> <examples> ✓ "What databases are on this server?" ✓ "Show me what's available" → call listDatabases first </examples> <what_it_returns> A sorted JSON array of database name strings. </what_it_returns> <pagination> Paginated. Pass the prior response's `nextCursor` as `cursor` to fetch the next page. </pagination> Input schemasha256:9008030b75767a318fb9b2cb2cf444105f0337dcca92875cbaff72fd5a5a6519Output schemasha256:ad6956198d5e301b3f9bf1c312499230342cb08de1630e058660a920007193b7Description hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | No change observed | |
listFunctionshaymon-dbmcp:tool:listFunctionsObserved interface and hashesList user-defined SQL functions in a database, optionally filtered and/or with full metadata. Loadable UDFs (`mysql.func`) and stored procedures are excluded. <usecase> Use when: - Auditing stored functions across a database (brief mode, default). - Searching for a function by partial name (pass `search`). - 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`. </usecase> <parameters> - `database` — Database to target. Defaults to the active database. - `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`. - `search` — Case-insensitive filter on function names via `LIKE`. `%` matches any sequence; `_` matches a single character. - `detailed` — When `true`, returns full metadata objects keyed by function name instead of bare name strings. Default `false`. </parameters> <examples> ✓ "What functions are in the mydb database?" → listFunctions(database="mydb") ✓ "Find the order-total calculation" → listFunctions(search="order") ✓ "What does calc_order_total do?" → listFunctions(search="calc_order_total", detailed=true) ✗ "List stored procedures" → use listProcedures instead ✗ "List loadable UDFs from mysql.func" → not supported; only routines in information_schema.ROUTINES are returned </examples> <what_it_returns> Brief mode (default): a sorted JSON array of function-name strings, e.g. `["calc_order_subtotal", "calc_order_total", "double_it"]`. Detailed 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. </what_it_returns> <pagination> Paginated. 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. </pagination> Input schemasha256:b7f37d65b2ddea36850898f7a44bf1c53cee967bdce9c15c3f42d33aa7e51277Output schemasha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27dDescription hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | No change observed | |
listProcedureshaymon-dbmcp:tool:listProceduresObserved interface and hashesList user-defined stored procedures in a database, optionally filtered and/or with full metadata. Stored functions and loadable UDFs (`mysql.func`) are excluded. <usecase> Use when: - Auditing stored procedures across a database (brief mode, default). - Searching for a procedure by partial name (pass `search`). - 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`. </usecase> <parameters> - `database` — Database to target. Defaults to the active database. - `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`. - `search` — Case-insensitive filter on procedure names via `LIKE`. `%` matches any sequence; `_` matches a single character. - `detailed` — When `true`, returns full metadata objects keyed by procedure name instead of bare name strings. Default `false`. </parameters> <examples> ✓ "What procedures are in the mydb database?" → listProcedures(database="mydb") ✓ "Find the order archival routine" → listProcedures(search="archive") ✓ "What does archive_order do?" → listProcedures(search="archive_order", detailed=true) ✗ "List functions" → use listFunctions instead ✗ "List loadable UDFs from mysql.func" → not supported; only routines in information_schema.ROUTINES are returned </examples> <what_it_returns> Brief mode (default): a sorted JSON array of procedure-name strings, e.g. `["archive_order", "archive_order_history", "purge_order_archive", "touch_post"]`. Detailed 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). </what_it_returns> <pagination> Paginated. 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. </pagination> Input schemasha256:17b4d9b8bff89f3037a50a8b98bf26028031f26d77ab2136fa7603bc50c31b5eOutput schemasha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27dDescription hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | No change observed | |
listTableshaymon-dbmcp:tool:listTablesObserved interface and hashesList tables in a database, optionally filtered and/or with full metadata. <usecase> Use when: - Exploring a database to find relevant tables (brief mode, default). - Searching for a table by partial name (pass `search`). - Inspecting a table's columns, constraints, indexes, and triggers before writing a query (pass `detailed: true`). </usecase> <parameters> - `database` — Database to target. Defaults to the active database. - `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`. - `search` — Case-insensitive filter on table names via `LIKE`. `%` matches any sequence; `_` matches a single character. - `detailed` — When `true`, returns full metadata objects keyed by table name instead of bare name strings. Default `false`. </parameters> <examples> ✓ "What tables are in mydb?" → listTables(database="mydb") ✓ "Find the orders table" → listTables(search="order") ✓ "What columns does orders have?" → listTables(search="orders", detailed=true) </examples> <what_it_returns> Brief mode (default): a sorted JSON array of table-name strings, e.g. `["customers", "orders"]`. Detailed 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", …}}`. </what_it_returns> <pagination> Paginated. 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. </pagination> Input schemasha256:9a7849de585a58c6c4a0aff6bcd893486c470afc0a7f45487d3ddcfcc29bfd33Output schemasha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27dDescription hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | No change observed | |
listTriggershaymon-dbmcp:tool:listTriggersObserved interface and hashesList user-defined triggers in a database, optionally filtered and/or with full metadata. <usecase> Use when: - Auditing trigger coverage across a database (brief mode, default). - Searching for a trigger by partial name (pass `search`). - 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`. </usecase> <parameters> - `database` — Database to target. Defaults to the active database. - `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`. - `search` — Case-insensitive filter on trigger names via `LIKE`. `%` matches any sequence; `_` matches a single character. - `detailed` — When `true`, returns full metadata objects keyed by trigger name instead of bare name strings. Default `false`. </parameters> <examples> ✓ "What triggers are in the mydb database?" → listTriggers(database="mydb") ✓ "Find the audit triggers" → listTriggers(search="audit") ✓ "What does orders_audit_after_insert do?" → listTriggers(search="orders_audit_after_insert", detailed=true) ✗ "Show me a trigger's body" → use detailed mode; the `definition` field carries the full `CREATE TRIGGER` text </examples> <what_it_returns> Brief mode (default): a sorted JSON array of trigger-name strings, e.g. `["customers_audit_after_insert", "orders_audit_after_insert"]`. Detailed 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. </what_it_returns> <pagination> Paginated. 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. </pagination> Input schemasha256:185159c7e34274bc598f91181da7b69b0fd4aee11a860e8dc2c96e070c543c72Output schemasha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27dDescription hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | No change observed | |
listViewshaymon-dbmcp:tool:listViewsObserved interface and hashesList user-defined views in a database, optionally filtered and/or with full metadata. Base tables and system-schema views are excluded. <usecase> Use when: - Auditing views across a database (brief mode, default). - Searching for a view by partial name (pass `search`). - 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`. </usecase> <parameters> - `database` — Database to target. Defaults to the active database. - `cursor` — Opaque pagination cursor; echo the prior response's `nextCursor`. - `search` — Case-insensitive filter on view names via `LIKE`. `%` matches any sequence; `_` matches a single character. - `detailed` — When `true`, returns full metadata objects keyed by view name instead of bare name strings. Default `false`. </parameters> <examples> ✓ "What views are in the mydb database?" → listViews(database="mydb") ✓ "Find the active-users view" → listViews(search="active") ✓ "What does active_users select?" → listViews(search="active_users", detailed=true) ✗ "Show me the columns of a view" → use listTables with `detailed: true` instead ✗ "List materialized views" → MySQL/MariaDB have no materialized-view concept </examples> <what_it_returns> Brief mode (default): a sorted JSON array of view-name strings, e.g. `["active_orders", "active_users", "published_posts"]`. Detailed 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. Versus 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. </what_it_returns> <pagination> Paginated. 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. </pagination> Input schemasha256:00ca76677e1c81f69370ab241f849f579abc2d2f70831d1a33de1942390977ebOutput schemasha256:17deee57a8ee723dcb3148870391f5a07a73a46c332c5b211192f0c55c8ba27dDescription hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | No change observed | |
readQueryhaymon-dbmcp:tool:readQueryObserved interface and hashesExecute a read-only SQL query. Allowed statements: SELECT, SHOW, DESCRIBE, EXPLAIN. <usecase> Use when: - Querying data from tables (SELECT with WHERE, JOIN, GROUP BY, etc.) - Aggregations: COUNT, SUM, AVG, GROUP BY, HAVING - Listing server variables or status (SHOW) - Viewing table structure (DESCRIBE) </usecase> <when_not_to_use> - Data changes (INSERT, UPDATE, DELETE) → use writeQuery (not available in read-only mode) - Query performance analysis → use explainQuery - Discovering tables or columns → use listTables (pass detailed=true for column-level metadata) - Switching database context (USE is rejected) → pass the `database` argument </when_not_to_use> <examples> ✓ "SELECT * FROM users WHERE status = 'active'" ✓ "SELECT COUNT(*) FROM orders GROUP BY region" ✓ "SHOW TABLES" or "DESCRIBE users" ✗ "INSERT INTO users ..." → use writeQuery (not available in read-only mode) ✗ "EXPLAIN SELECT ..." → use explainQuery for structured analysis </examples> <what_it_returns> A JSON array of row objects, each keyed by column name. Long 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`. </what_it_returns> <pagination> `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. Pages stay within the statement's own `LIMIT` and `OFFSET`. Write a row limit as a literal `LIMIT n`: other forms (`FETCH FIRST`, expressions) make every page read the whole result. `SHOW`, `DESCRIBE`, and `EXPLAIN` return a single page and ignore `cursor`. </pagination> <timeout> Each 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. </timeout> Input schemasha256:cd507ff6a3b1cbd852bcdba947b971fe4a3ad4ae70bcaf0caa67f3cd04cef204Output schemasha256:999feb2ae8d32aab91030cb9c6f1ffa7c18de6779187e5ddf2e4344c34e4d1deDescription hash: Interface hash: Other observed Modelara metadata | tool | 0.18.0 | 0.19.0 |
No capabilities match these filters.
STATIC COMPARISONS
Release history
- 0.18.1 0.19.0PASS0 added0 removed0 schema0 write0 destructive0 unknown
- 0.18.0 0.18.1PASS0 added0 removed0 schema0 write0 destructive0 unknown