AI and MCP

Connect AI agents and IDEs to PostgreSQL through pREST’s read-only Model Context Protocol (MCP) endpoint. Use the same server that already exposes a REST API from PostgreSQL — no separate query service required.

pREST v2.1.0+ ships HTTP MCP at /_mcp. Clients that only speak stdio (Cursor, VS Code / Copilot, Claude Desktop, and many others) use the official pREST MCP Adapter (prest-mcp) as a transport bridge.

---

What you get

Piece	Role
pREST /_mcp	Read-only MCP tools: list databases/schemas/tables, describe columns, select rows (max 100)
prest-mcp adapter	Stdio ↔ HTTP bridge only — does not introspect schemas, generate SQL, or implement tools
pREST for Cursor	Optional Cursor plugin (rules and skills) — separate from the MCP binary
pREST for OpenClaw	Optional OpenClaw plugin (skills and examples) — separate from the MCP binary

Cursor / VS Code / Claude / OpenClaw / Cline / Continue
        ↓ stdio
   prest-mcp
        ↓ HTTP POST
   prestd /_mcp
        ↓
   PostgreSQL

---

Start here

1. MCP Overview — architecture, adapter vs server, security

2. Install pREST MCP Adapter — Homebrew, Go, Docker, MCP Registry

3. Pick a client:

   • Use with Cursor

   • Use with VS Code and Copilot

   • Use with Claude Desktop

   • Other AI tools (Cline, Continue, Windsurf, OpenClaw, generic stdio)

4. Read-only PostgreSQL for AI — least-privilege role for agent access

5. Optional agent plugins: pREST for Cursor · pREST for OpenClaw

End-to-end walkthrough: PostgreSQL to AI agent.

---

Protocol reference

Deep tools, auth, ACL, and JSON-RPC details stay in MCP over HTTP. This AI section focuses on install and client setup.

---

Next steps

• Install the adapter: Install pREST MCP Adapter or Homebrew tutorial

• Run pREST locally: Get pREST · Distribution channels

• Confirm discovery: curl -s http://localhost:3000/_mcp