{"id":"pg-metadata-mcp-server","name":"pg-metadata-mcp-server","homepage":"https://pypi.org/project/pg-metadata-mcp-server/","repo_url":null,"category":"devtools","subcategories":[],"tags":["mcp","postgres","database-metadata","schema-introspection","ai-agents"],"what_it_does":"Provides an MCP (Model Context Protocol) server for accessing/inspecting pg-metadata (PostgreSQL metadata). It is intended to let AI agents query database metadata via MCP tools rather than direct DB connections.","use_cases":["AI agents that need to understand database schema/relations (tables, columns, types)","Generating SQL or migration plans using up-to-date Postgres metadata","Building admin/debug tooling for Postgres environments via agent-driven metadata lookup"],"not_for":["Writing/committing database changes (DDL/DML) unless explicitly provided as separate tools","Handling production traffic workloads with strict uptime/SLA requirements (unless documented)","Environments where outbound network access to the MCP server is not allowed"],"best_when":"You want an LLM/agent workflow to fetch Postgres metadata on-demand through MCP tool calls.","avoid_when":"You require strong guarantees about rate limits, auth, and structured error contracts that are not documented by the package.","alternatives":["Direct Postgres access via a DB driver/ORM + schema introspection","dbt/Schema export tools (schema.yml generation)","Other MCP servers focused on database schema introspection (if available)"],"af_score":32.8,"security_score":31.8,"reliability_score":26.2,"package_type":"mcp_server","discovery_source":["pypi"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:48:45.500405+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["unknown"],"oauth":false,"scopes":false,"notes":"No auth details were provided in the supplied information, so auth method and scope granularity cannot be confirmed."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":null},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":32.8,"security_score":31.8,"reliability_score":26.2,"mcp_server_quality":55.0,"documentation_accuracy":30.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":30.0,"rate_limit_clarity":0.0,"tls_enforcement":50.0,"auth_strength":25.0,"scope_granularity":10.0,"dependency_hygiene":50.0,"secret_handling":30.0,"security_notes":"Without provided implementation details, TLS/auth/secret handling cannot be confirmed. MCP servers that connect to Postgres typically require careful handling of DB credentials and principle-of-least-privilege DB roles; ensure the tool does not expose sensitive metadata beyond necessity.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":40.0,"error_recovery":25.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["MCP tool behaviors (timeouts, pagination, and error formats) may be undocumented or inconsistent across implementations","Agents may assume DB schema completeness; metadata can be stale depending on connection/role/permissions","Metadata queries can be slow on large catalogs without caching/limits"]}}