describe_agent — agent provenance MCP Tool Read-only
describe_agent
(describe agent) is one of 11 tools on the
agent provenance
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call describe_agent from your client
- Claude Code agent provenance describe_agent run in your project directory
- Claude Desktop agent provenance describe_agent ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor agent provenance describe_agent ~/.cursor/mcp.json
- VS Code agent provenance describe_agent .vscode/mcp.json
- Zed agent provenance describe_agent ~/.config/zed/settings.json
- Windsurf agent provenance describe_agent ~/.codeium/windsurf/mcp_config.json
- Cline agent provenance describe_agent ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI agent provenance describe_agent ~/.gemini/settings.json
- Grok agent provenance describe_agent .mcp.json (in your project root)
- ChatGPT agent provenance describe_agent Settings → Connectors → Advanced → Developer mode
- Claude.ai agent provenance describe_agent Settings → Connectors → Add custom connector
- LangChain agent provenance describe_agent pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agent-provenance https://mcp.viridisconservation.com/provenance/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.