Monte Carlo MCP Server
A first-party, fully hosted Model Context Protocol server that gives AI agents direct access to Monte Carlo — investigating alerts, exploring assets and lineage, creating and tuning monitors, and evaluating AI agent performance. 56 documented tools across three toolsets (default, extended, agent_observability) plus four published MCP prompts. Reached over streamable HTTP with OAuth 2.1 and dynamic client registration, or with MCP-scoped keys; also shipped as an Anthropic-verified connector in the Claude Connectors Directory. Runs on AWS Lambda, stateless, executing under the calling user's Monte Carlo identity.