Postgres MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/pgedge-postgres-mcp

About

Use cases: database-access, knowledge-base

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

7 read · 3 write · 0 delete · 1 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Docker image

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• authenticate_user

  Authenticates a user and returns a session token for subsequent API calls. This tool is for direct client use only and is not advertised to the LLM.

• count_rows

  Get the row count of a table with optional filtering. Use this tool instead of running SELECT COUNT(*) through psql or shell commands — it provides efficient counting with proper access control. <usecase> Use count_rows to efficiently determine data volume: - Check total row count before querying large tables - Verify filter conditions match expected number of rows - Plan query strategies based on data size - Validate data existence without fetching rows </usecase> <examples> ✓ count_rows(table="orders") → Total orders in database ✓ count_rows(table="orders", schema="sales") → Orders in sale…

• execute_explain

  Execute EXPLAIN ANALYZE on a query to diagnose performance. Use this tool instead of running EXPLAIN directly through psql — it provides structured analysis with optimization recommendations. <usecase> Use when: - Query runs slowly and you need to understand why - Investigating performance bottlenecks - Planning index creation to optimize queries - Understanding query execution strategy - Analyzing join performance and table scan methods </usecase> <what_it_returns> Returns a detailed execution plan with: - Query execution time and planning time - Actual row counts vs estimated row counts - …

• generate_embedding

  Generate embedding vector from text using the configured provider (OpenAI, Anthropic Voyage, or Ollama). Use this tool instead of calling embedding APIs directly — it handles provider configuration and returns vectors ready for storage or semantic search operations.

• get_schema_info

  Discover database structure and available tables. Use this tool instead of psql meta-commands (\dt, \d, \dn) or information_schema queries — it provides comprehensive schema details with filtering and token-efficient output. <usecase> Use get_schema_info when you need to: - Discover what tables exist in the database - Understand table structure (columns, types, constraints) - Find tables with specific capabilities (e.g., vector columns) - Learn column names before writing queries - Check data types, nullable, and unique constraints - Understand primary/foreign key relationships for JOINs </us…

• list_database_connections

  List available database connections that you can switch to. Use this tool instead of checking connection parameters manually — it shows all configured databases with their status. Returns a list of database connections configured for this session, along with the currently active database. Use this to discover what databases are available before using select_database_connection to switch. Each database entry includes: - name: The connection name (use this with select_database_connection) - database: The PostgreSQL database name - host: Database server hostname (first configured host for multi…

• query_database

  Description is built at runtime.

• read_resource

  Read MCP resources via tool interface (backward compatibility). <important> This tool provides backward compatibility with older MCP clients. Modern MCP clients should use the native resources/read endpoint instead, which is more efficient and follows MCP standards. </important> <usecase> Use read_resource when: - Your MCP client doesn't support native resources/read endpoint - You need resource content as tool output (not native resource format) - Building tool-only workflows without resource support - Testing or debugging resource access </usecase> <available_resources> 1. pg://system_inf…

• search_knowledgebase

  Search the pre-built documentation knowledgebase for relevant information. <critical> IMPORTANT: Product names require EXACT matches. "pgEdge" will NOT match "pgEdge RAG Server", "pgEdge Cloud", or "pgEdge Platform" - these are separate products. ALWAYS call with list_products=true FIRST to discover exact product names before filtering by project_names. </critical> Use this tool when you need information about: - PostgreSQL features, syntax, functions - pgEdge products and capabilities - Other documented products and technologies The knowledgebase contains chunked, embedded documentation f…

• select_database_connection

  Switch to a different database connection for subsequent queries. Use this tool instead of reconnecting through psql — it manages connection lifecycle and preserves session state. Use list_database_connections first to see available options. After switching, all subsequent database tools (query_database, get_schema_info, etc.) will operate on the newly selected database. IMPORTANT: Switching databases may change available schemas, tables, and permissions. Consider re-examining the schema after switching.

• similarity_search

  ⚠️ IMPORTANT: Use this tool to retrieve database content BEFORE answering questions about it. Do NOT answer from memory! Semantic search for NATURAL LANGUAGE and CONCEPT-BASED queries. Use this tool instead of manual text search queries through psql — it combines vector similarity with lexical ranking for superior results. <critical_usage_note> MANDATORY RULE: When a user asks about content that you know EXISTS in the database (e.g., "tell me about X", "what is Y", "describe Z", "summarize A", "what are the capabilities of X"), you MUST ALWAYS use this tool FIRST to retrieve the current inf…

Compare and alternatives

Featured in

• Best MCP servers for Postgres
• Best MCP servers for vector search and databases

Signals

Stars

240

Forks

24

Open issues

6

Contributors

19

Last commit

Sep 28, 2026 (1 month ago)

Last release

Sep 4, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.pgEdge/postgres-mcp

Version

1.0.0

Auth

No auth

Packages

oci ghcr.io/pgedge/postgres-mcp:latest

License

PostgreSQL

Repository

github.com/pgEdge/pgedge-postgres-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql