MCP Server
Remote MCP endpoint for AI agent integration.
POST /v1/mcp is a remote Model Context Protocol
server using the Streamable HTTP transport. It exposes every public API
operation as an MCP tool so AI assistants can manage PgBeam resources directly.
See the MCP command docs for full setup instructions covering both the CLI (stdio) and remote (HTTP) transports.
Quick start
curl -X POST https://api.pgbeam.com/v1/mcp \
-H "Authorization: Bearer pbk_..." \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2025-03-26",
"capabilities": {},
"clientInfo": { "name": "my-agent", "version": "1.0" }
}
}'Protocol
| Property | Value |
|---|---|
| Transport | Streamable HTTP (MCP spec 2025-03-26) |
| Wire format | JSON-RPC 2.0 |
| Auth | Authorization: Bearer <token> |
| Methods | initialize, notifications/initialized, tools/list, tools/call, ping |
Authentication
The MCP endpoint uses the same authentication as the REST API. Pass a bearer
token or API key in the Authorization header. See Authentication.
Tools
Tools are auto-generated from the OpenAPI spec. Each public endpoint becomes a
tool named after its operationId. Arguments map to path parameters, query
parameters, and an optional body object for mutating methods.
Call tools/list to discover all available tools and their input schemas.