An MCP server that wraps AI coding agents as callable tools, enabling an MCP client to delegate coding tasks to Claude Code, GitHub Copilot CLI, or OpenCode. Provides dispatch tools for task execution and monitoring, and bounded plan tools for constrained execution with safety guardrails including file restrictions and verification checks. Each agent integration exposes estimated cost, supported task types, and execution status.
Cognium trust score
100%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.