llm-observability-orchestration
MCP serverMonitoring & opsLets your agent run prompts through a LangChain system+human chain on Google Gemini using an LLM MCP server.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the invoke tool from llm-observability-orchestration
About this server
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Install llm-observability-orchestration
The server’s own address, for the clients that take one directly. Or connect ahel onceand every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.
Claude Code
claude mcp add --transport http --scope user llm-observability-orchestration 'https://langchain-core-langsmith-openai-8c02f9.getvda.ai/mcp'Run it once in your project, then open /mcp to approve any sign-in the server asks for.
Claude Desktop
https://langchain-core-langsmith-openai-8c02f9.getvda.ai/mcpAdd a custom connector in Settings, paste this address, and approve the sign-in.
Cursor
cursor://anysphere.cursor-deeplink/mcp/install?name=llm-observability-orchestration&config=eyJ1cmwiOiJodHRwczovL2xhbmdjaGFpbi1jb3JlLWxhbmdzbWl0aC1vcGVuYWktOGMwMmY5LmdldHZkYS5haS9tY3AifQ==Open the link and Cursor adds the server at that address.
ChatGPT
https://langchain-core-langsmith-openai-8c02f9.getvda.ai/mcpIn Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.
Codex
codex mcp add llm-observability-orchestration --url 'https://langchain-core-langsmith-openai-8c02f9.getvda.ai/mcp'Run it once, then sign in with codex mcp login llm-observability-orchestration if the server asks for an account.
From the project's README
As published by mikerawsonnz/gosce-agents in README.md. This repository publishes several servers, so only the opening is shown here.
A portfolio of production remote MCP + A2A agents running on getvda.ai, discovered + quality-assured by the GOSCE Portfolio Router. Each agent is capability-scoped, speaks open A2A + MCP, and is metered with Nevermined x402 micropayments (discovery is free).
Generated by GOSCE (GitHub Open-Source Combination Engine) — an automated pipeline that mines the OSS dependency graph for monetizable package combinations and deploys each as a verified agent.
Agents
| Agent | Capability | Docs |
|---|---|---|
| Authenticated Multi-LLM Agent | oauth-llm | README · Smithery |
| Traced LLM Proxy | traced-gemini | README · Smithery |
| ai.getvda/bcrypt-langchain-core-mcp-25b8f1 | auth-llm | README · Smithery |
| [Authenticated LL |
Shortened here. Read the whole README on GitHub.
Tools it offers (2)
What this server listed when ahel dialed its public endpoint in Sep 2026, with no key and no account of yours. The names are the server’s own.
invokeselftest
Signals
- GitHub stars
- 1
- Last commit
- Sep 2026
Advanced
- Delivery
- llm-observability-orchestration MCP server → your ahel connector (mcp.ahel.ai) → your AI.
- Item type
- mcp-server
- Key
io-github-mikerawsonnz-llm-observability-orchestration- Source
- github.com/mikerawsonnz/gosce-agents
- Hosted endpoint
https://langchain-core-langsmith-openai-8c02f9.getvda.ai/mcp