postgres-mcp-server
This server enables interaction with PostgreSQL databases through the Model Context Protocol, optimized for the AWS Bedrock AgentCore Runtime. It provides tools for executing read-only queries, exploring database schemas, and monitoring table statistics or slow queries.
README
postgres-mcp-server
A Postgres MCP server built for AWS Bedrock AgentCore Runtime.
AgentCore Protocol Compliance
- Transport: Stateless streamable-http (
stateless_http=True) - Port: 8000 on
0.0.0.0 - Path:
POST /mcp - Platform: ARM64 container
- Framework: Python FastMCP
Tools
| Tool | Description |
|---|---|
query |
Execute read-only SQL queries (runs in READ ONLY transaction) |
list_tables |
List tables in a schema with row counts and sizes |
describe_table |
Column details, constraints, and indexes for a table |
list_schemas |
List all non-system database schemas |
explain_query |
Get EXPLAIN plan for a query (optionally with ANALYZE) |
get_table_stats |
Row counts, sizes, scan stats, vacuum info |
get_slow_queries |
Top slow queries from pg_stat_statements |
Environment Variables
| Variable | Required | Description |
|---|---|---|
POSTGRES_URL |
Yes* | PostgreSQL connection string |
DATABASE_URI |
Yes* | Alternative name for connection string |
*One of POSTGRES_URL or DATABASE_URI is required.
Security
- All queries execute inside
READ ONLYtransactions - Point
POSTGRES_URLat a read replica for hard DB-level enforcement - Use a Postgres user with
SELECT-only grants for defense in depth
Local Development
# Run directly
POSTGRES_URL="postgresql://user:pass@localhost:5432/mydb" python server.py
# Run with Docker
docker build -t postgres-mcp .
docker run -e POSTGRES_URL="postgresql://user:pass@host:5432/mydb" -p 8000:8000 postgres-mcp
Deploy to AgentCore
# Build for ARM64
docker buildx build --platform linux/arm64 -t <ecr-uri>/pgmcp:latest --push .
# Create runtime
aws bedrock-agentcore-control create-agent-runtime \
--agent-runtime-name "mcp_postgres" \
--agent-runtime-artifact '{"containerConfiguration":{"containerUri":"<ecr-uri>/pgmcp:latest"}}' \
--protocol-configuration '{"serverProtocol":"MCP"}' \
--environment-variables '{"POSTGRES_URL":"postgresql://...","PORT":"8000"}' \
--network-configuration '{"networkMode":"VPC","networkModeConfig":{"securityGroups":["sg-xxx"],"subnets":["subnet-xxx"]}}' \
--role-arn "arn:aws:iam::xxx:role/agentcore-execution"
Test
# Health check (via MCP initialize)
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'
# List tools
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}'
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.