postgres-mcp-server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@postgres-mcp-servershow me the schema and indexes for the users table"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
0.0.0.0Path:
POST /mcpPlatform: ARM64 container
Framework: Python FastMCP
Tools
Tool | Description |
| Execute read-only SQL queries (runs in |
| List tables in a schema with row counts and sizes |
| Column details, constraints, and indexes for a table |
| List all non-system database schemas |
| Get EXPLAIN plan for a query (optionally with ANALYZE) |
| Row counts, sizes, scan stats, vacuum info |
| Top slow queries from pg_stat_statements |
Environment Variables
Variable | Required | Description |
| Yes* | PostgreSQL connection string |
| Yes* | Alternative name for connection string |
*One of POSTGRES_URL or DATABASE_URI is required.
Security
All queries execute inside
READ ONLYtransactionsPoint
POSTGRES_URLat a read replica for hard DB-level enforcementUse 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-mcpDeploy 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"}'This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/madhurprash/postgres-mcp-agentcore'
If you have feedback or need assistance with the MCP directory API, please join our Discord server