A local MCP server that exposes the SAIR Competition Public API as tools for MCP clients, enabling account introspection, competition browsing, submissions, playground operations, cheatsheet management, and Contributor Network interactions.
MCP server for AgentMark. Exposes the full AgentMark API to AI editors: list traces and spans, manage datasets, write scores, run experiments, manage apps, deployments, environments, and annotation queues.
MCP server for orchestrating coding tasks with frontier-model planning and local execution, enabling manifest validation, plan submission, status checks, cancellation, and report retrieval through Claude Code.