MCP server (Streamable HTTP)

Model Context Protocol endpoint using the Streamable HTTP transport. Accepts JSON-RPC 2.0 requests and exposes every public API operation as an MCP tool. Use this with any MCP-compatible client (Claude Code, Cursor, Windsurf, custom agents) to let AI assistants manage PgBeam resources.

Transport: Streamable HTTP (MCP spec 2025-03-26) Protocol: JSON-RPC 2.0 Methods: initialize, tools/list, tools/call, ping

Prefer the CLI (pgbeam mcp) for local stdio transport. Use this endpoint for remote or server-to-server MCP integration.

At a glance

Quick request

Use this as a starting point. Replace the placeholder IDs, set PGBEAM_TOKEN, and create body.json from the schema below.

curl -X POST \
  "$PGBEAM_API_URL/v1/mcp" \
  -H "Authorization: Bearer $PGBEAM_TOKEN" \
  -H "Content-Type: application/json" \
  --data @body.json

curl -X POST "https://api.pgbeam.com/v1/mcp" \  -H "Content-Type: application/json" \  -d '{    "jsonrpc": "2.0",    "id": "1",    "method": "initialize",    "params": {      "protocolVersion": "2025-03-26",      "capabilities": {},      "clientInfo": {        "name": "my-agent",        "version": "1.0.0"      }    }  }'

{
  "jsonrpc": "2.0",
  "id": "string",
  "result": {},
  "error": {
    "code": 0,
    "message": "string"
  }
}

{
  "error": {
    "code": "string",
    "message": "string"
  }
}

{
  "error": {
    "code": "string",
    "message": "string"
  }
}