Polyagent (Claude Code Agents)
Polyagent MCP bridges Claude Code's agent definitions to any MCP client, enabling AI coding assistants like Codex and Gemini CLI to access Claude-style specialized agents. Built by Andrew Konstantinov using FastMCP, it automatically discovers agent files with YAML front matter containing metadata like name, description, model, and tools, then exposes them as MCP resources and prompts. The implementation includes a hybrid YAML parser that gracefully handles both valid YAML and malformed YAML that Claude Code sometimes generates (like unquoted values with colons and literal escape sequences), ensuring compatibility with real-world agent files. Valuable for teams wanting to share and reuse Claude Code agents across different AI development environments without being locked into a single platform.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/execveat/polyagent-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Polyagent (Claude Code Agents) from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.