selftest — llm observability orchestration agent langchain community MCP Tool
selftest
(selftest) is one of 2 tools on the
llm observability orchestration agent langchain community
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call selftest from your client
- Claude Code llm observability orchestration agent langchain community selftest run in your project directory
- Claude Desktop llm observability orchestration agent langchain community selftest ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor llm observability orchestration agent langchain community selftest ~/.cursor/mcp.json
- VS Code llm observability orchestration agent langchain community selftest .vscode/mcp.json
- Zed llm observability orchestration agent langchain community selftest ~/.config/zed/settings.json
- Windsurf llm observability orchestration agent langchain community selftest ~/.codeium/windsurf/mcp_config.json
- Cline llm observability orchestration agent langchain community selftest ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI llm observability orchestration agent langchain community selftest ~/.gemini/settings.json
- Grok llm observability orchestration agent langchain community selftest .mcp.json (in your project root)
- ChatGPT llm observability orchestration agent langchain community selftest Settings → Connectors → Advanced → Developer mode
- Claude.ai llm observability orchestration agent langchain community selftest Settings → Connectors → Add custom connector
- LangChain llm observability orchestration agent langchain community selftest pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http llm-observability-orchestration-agent-langchain-community https://llm-observability-orchestration-agent-langchai-c1a755.getvda.ai/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.