Postgres Developer Loadout
4 MCP servers for daily Postgres work with Claude and Cursor
Last verified:
A read-mostly stack for backend engineers who write SQL every day. Inspect schemas before migrations, draft queries against real data, and let the agent open PRs against your repo without leaving the chat.
Install Postgres Developer Loadout
Paste into~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/Users/you/projects"]
},
"postgres": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://readonly@localhost:5432/mydb"]
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..." }
},
"memory": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-memory"]
}
}
}After pasting, fully restart your MCP client. Replace placeholders (paths, API keys) with your own values.
What's in this loadout
- Filesystem MCP Servercoremcp
Read project files (migrations, schema dumps, .env.example) so the agent can ground its answers in your code.
- Postgres MCP Servercoremcp
Read-only queries with schema introspection. The core of this loadout — the agent inspects your DB before suggesting any change.
- GitHub MCP Servercoremcp
Open PRs with new migrations and review existing ones. Ties database changes to a code review trail.
- Memory MCP Serveroptionalmcp
Persist schema notes between sessions so you don't re-explain your data model every chat.
What you can do with it
Find slow queries and suggest indexes
Using the postgres MCP, list queries from pg_stat_statements over 500ms in the last 7 days, then check the schema and suggest missing indexes. Save findings to a file in /Users/me/db-audit.Draft a safe migration
Read /Users/me/repo/migrations/, infer the current schema, then draft a migration that adds a NOT NULL column with a backfill default. Open a PR on github with the migration and a rollback note.Explain unfamiliar tables
Connect to the production replica, list every table whose name starts with "billing_", and for each one summarise its columns, foreign keys, and how it relates to the customers table.
Client compatibility
- Claude Desktop 0.7.4Tested ✓
- Cursor 0.42+Tested ✓
- Windsurf 1.4Tested ✓
- Continue 0.9Untested
Variants
Heavy version
Adds Sentry for error correlation and Linear so the agent can file bugs it discovers.
Adds: mcp-server-sentry, mcp-server-linear
Lite version
Just Filesystem + Postgres. Enough to inspect the DB and your local code.
Removes: mcp-server-github, mcp-server-memory
FAQ — Postgres Developer Loadout
What is the Postgres Developer Loadout?
A read-mostly stack for backend engineers who write SQL every day. Inspect schemas before migrations, draft queries against real data, and let the agent open PRs against your repo without leaving the chat. It includes 4 MCP servers: Filesystem MCP Server, Postgres MCP Server, GitHub MCP Server, Memory MCP Server.
Does this loadout work with Cursor and Windsurf?
Yes. The config block above is one JSON object that drops into Claude Desktop's, Cursor's, or Windsurf's MCP config. Each client uses the same mcpServers schema; only the file path differs.
How long does setup take?
About 3 minutes the first time: copy the config, paste it into your client's MCP configuration file, replace placeholder API keys with your own, and restart the client.
Can I customise this loadout?
Yes. Use the Lite version if you want fewer servers, or the Heavy version to add 2 more for advanced workflows. You can also remove any individual server by deleting its entry from the JSON.
How much does it cost?
Loadout itself is free. Most listed servers are open-source and free to run. Servers that talk to paid SaaS (Stripe, SendGrid, Linear, etc.) follow that vendor's pricing.
When was this loadout last verified?
Last verified on 2026-04-24. We re-test featured loadouts at least monthly and update the config when MCP servers ship breaking changes.