sql-mcp
Related Servers
Alternatives to sql-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to safely explore and query SQL databases through read-only, AST-checked SQL, database-enforced read-only transactions, timeouts, row caps, PII masking, and audit logging.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to securely discover database schemas and execute read-only SQL queries through guardrailed tools that block mutations and clamp result sizes.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI applications to discover MySQL and PostgreSQL database schemas and run validated read-only SELECT queries against a configured database, with result limits and SQL safety controls.20MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to run read-only SQL against SQLite or MySQL databases through MCP tools for listing tables, describing schemas, and querying data. Wraps every call in guardrails such as statement allow-listing, row caps, query timeouts, PII masking, and audit logging.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query Postgres, BigQuery and DuckDB read-only through policy-checked SQL, with AST-based guards that refuse writes and dangerous functions, column masking on the way out, and an audit log of every query. Also exposes schema browsing and query-planning tools so agents can see allowed tables, columns and costs before running anything.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to safely explore and query SQLite or PostgreSQL databases through read-only, guarded SELECT queries with column masking, row limits, timeouts, and audit logging.MIT
TDQS
Scored across 8 tools
Each tool has a distinct purpose: metadata discovery (list_profiles, list_databases, list_tables, search_schema, describe_table), inspection (sample_rows, explain_query), and execution (execute_query). There is minor functional overlap—sample_rows and explain_query can both be approximated via execute_query—but the descriptions clearly distinguish their intended use, so an agent is unlikely to misselect.
All eight tools follow a consistent snake_case verb_noun pattern (list_profiles, describe_table, search_schema, execute_query, etc.). No mixed conventions or vague standalone verbs.
Eight tools is a well-scoped set for a read-only SQL inspection server, with each tool earning a clear place across discovery, introspection, and querying. Nothing feels redundant or missing at the count level.
The read-only lifecycle is well covered: connection selection, database/table listing, schema search, full table description with bidirectional FKs, sampling, plan explanation, and arbitrary read queries. Gaps are limited to write operations (intentional for a read-only server) and minor conveniences like standalone index listing.