LLM Observability & Orchestration Agent — Claude Code MCP server
LLM Observability & Orchestration Agent is an MCP server that runs LangChain prompts on Gemini in Vertex AI, optionally traces them in LangSmith, and returns an execution result and trust manifest from self-test.
no license 2,409 installs updated 2026-05-31
claude mcp add --transport http llm-observability-orchestration https://llm-observability-orchestration--a2a.run.toolsWhat LLM Observability & Orchestration Agent does
The invoke tool sends a prompt through a LangChain chain with system and human messages. It runs on Gemini in Vertex AI, and LangSmith tracing is optional. This gives an IDE agent a way to call the chain and inspect its execution.
Use selftest to run the agent against a fixed input. The response includes the result, an assertion grade and a trust manifest covering a signed Agent Card, JWKS, governance and licence details, and safety posture. Claims come with proof links. The server is accessed over MCP; configure its remote endpoint when connecting. invoke is tied to Gemini on Vertex AI.
What it helps with
- run a prompt through a LangChain chain
- send execution traces to LangSmith
- test the agent on a fixed input
- retrieve a trust manifest with proof links
Example prompts for the agent
- Run my prompt through the LangChain chain on Gemini in Vertex AI using
invoke. - Use
selftestand return the result with the trust manifest. - Run the prompt with LangSmith tracing enabled.
How to install LLM Observability & Orchestration Agent
Platform CLI: remote server
claude mcp add --transport http llm-observability-orchestration https://llm-observability-orchestration--a2a.run.toolsPlatform CLI: remote server
codex mcp add llm-observability-orchestration-agent --url https://llm-observability-orchestration--a2a.run.toolsConfig file
{
"mcpServers": {
"llm-observability-orchestration-agent": {
"url": "https://llm-observability-orchestration--a2a.run.tools"
}
}
}Config file
{
"servers": {
"llm-observability-orchestration-agent": {
"type": "http",
"url": "https://llm-observability-orchestration--a2a.run.tools"
}
}
}Platform CLI: remote server
gemini mcp add -t http llm-observability-orchestration-agent https://llm-observability-orchestration--a2a.run.toolsStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about LLM Observability & Orchestration Agent
How do I install LLM Observability & Orchestration Agent in Codex?
Add the MCP server with codex mcp add llm-observability-orchestration-agent --url https://llm-observability-orchestration--a2a.run.tools.
What does LLM Observability & Orchestration Agent do?
It runs prompts through a LangChain chain on Gemini in Vertex AI, with optional LangSmith tracing. Its selftest tool also returns a test result and trust manifest.
Which model does invoke use?
invoke runs the chain on Gemini in Vertex AI. LangSmith tracing can be enabled optionally.