RAKLEdocs
MCP

MCP Server

Orakle's pricing tools as a Model Context Protocol server for AI clients and agents.

View as Markdown

The Orakle MCP server exposes pricing intelligence as Model Context Protocol tools, so any MCP-capable AI client or headless agent can submit and read pricing jobs directly.

Endpoint:

https://api.orakle.xyz/v1/mcp

It speaks the Streamable HTTP transport (MCP spec 2025-11-25) and is stateless — no session is kept between requests. The endpoint accepts POST, GET, and DELETE.

Auth modes

  • OAuth 2.1 + PKCE — for interactive clients. The client discovers the authorization server, opens a browser for sign-in, and obtains a bearer token automatically. No manual token handling.
  • API key — for headless agents. Send your key as Authorization: Bearer sk_.... Create keys in your dashboard.

Connect

Add the server to any MCP-capable AI app or agent.

Tools

get_pricing, submit_pricing_job, get_job_result — inputs, outputs, examples.

When to use MCP

MCP wraps the same job system as the REST API and SDKs; read access is strictly per-user. Pick by where you work:

  • Inside an AI client or agent → MCP. The model calls the tools directly.
  • Application code (TypeScript/Python) → SDK. One call wraps submit → stream → result.
  • Any other stack or wire-level control → REST API.

TypeScript SDK

The orakle npm package — typed pricing jobs over SSE, with streaming callbacks and AbortSignal support.

Connect

Add the Orakle MCP server to any MCP-capable AI app or agent.

On this page

Auth modesWhen to use MCP