LangSmith Traced OpenAI Agent MCP

An MCP server that composes langchain-core, langchain-openai, langsmith, and openai for orchestration, observability, and LLM client interactions via A2A and MCP protocols. It allows agents to invoke tools like selftest and run prompts through a LangChain chain over Gemini on Vertex AI, with optional LangSmith integration.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by getvda.ai

MCP endpoint (Streamable HTTP)

https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp

Vendor documentation

What its tools do

2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

2 of 2 have a description · 0 of 2 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 5:42 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Invoke the selftest tool over MCP to verify agent capability
Run a prompt through a LangChain chain over Gemini on Vertex AI
Verify agent identity using signed Ed25519 JWS
Check assertion grades and trust manifests via selftest

Source and maintenance

Community listingRegistry 1.0.0

mcp-registry: io.github.mikerawsonnz/llm-orchestration-agent@1.0.0 Source repository Project website

Maintenance checked: Nov 6, 2026, 5:06 PM UTC

Protocol and capabilities

Server: langchain-core-langchain-openai-l-736876 0.1.1
MCP protocol negotiated in check: 2026-07-28
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Tools

2 advertised

invoke

Advertised by the server during the last successful anonymous check.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

invoke input schema

{
  "type": "object",
  "required": [
    "input"
  ],
  "properties": {
    "input": {
      "type": "string",
      "description": "JSON request for this capability (the same body you'd send as an A2A message)."
    }
  }
}

selftest

Advertised by the server during the last successful anonymous check.

FREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.

selftest input schema

{
  "type": "object",
  "properties": {}
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-06: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 628 ms
95th percentile latency: 628 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 5:42 PM UTC · probe · passed · 628 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http langsmith-traced-openai-agent-mcp https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add langsmith-traced-openai-agent-mcp --url https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable langsmith-traced-openai-agent-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "langsmith-traced-openai-agent-mcp": {
      "url": "https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "langsmith-traced-openai-agent-mcp": {
      "type": "streamableHttp",
      "url": "https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start langsmith-traced-openai-agent-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "langsmith-traced-openai-agent-mcp": {
      "type": "http",
      "url": "https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http langsmith-traced-openai-agent-mcp https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "langsmith-traced-openai-agent-mcp": {
      "serverUrl": "https://langchain-core-langchain-openai-l-736876.getvda.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like LangSmith Traced OpenAI Agent MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 4,794