An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Langsmith LLM Observability Hub to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Debug agentic workflows and manage prompts through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through LangSmith.

  1. 01

    List annotation queues

    This capability lists all active human-in-the-loop annotation queues. Use it to see where reviewers are currently grading model outputs.

  2. 02

    List datasets

    This capability retrieves all evaluation and fine-tuning datasets mapped in your LangSmith account. It helps you find the right data for testing new prompts.

  3. 03

    List prompts

    This capability pulls prompt templates directly from the LangChain Hub. It lets your agent access managed prompt versions and variable definitions.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through LangSmith.

  1. 04

    List runs

    This capability identifies specific LLM invocation runs within a chosen project. It isolates the raw interactions between your model and the user.

  2. 05

    Get run

    This capability fetches precise telemetry for a single LLM invocation. You can use it to check token counts, latency, and error strings for a specific run.

  3. 06

    List projects

    This capability maps out all active LangSmith tracing projects. It provides a high-level view of the different AI pipelines you are monitoring.

Real work

What teams actually run

01

Debugging Agentic Loops

When a multi-turn agent gets stuck, you can ask your client to inspect the internal reasoning paths and capability calls.

02

Prompt Version Control

Retrieve specific versions of a prompt from the Hub to compare how changes affect model output.

03

Latency Monitoring

Check the exact latency and token usage of a specific production run to optimize costs and speed.

04

Quality Assurance

Access evaluation datasets to run automated tests on new prompt logic or few-shot models.

Automate a task

Put LangSmith to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

LangSmith works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put LangSmith to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

902ms average. Fast in production.

LangSmith is checked daily against the live service.

Daily averagePeak 1067ms
Oct 3Today
Fastest day
732ms
Slowest day
1067ms
14-day trend
Slowing+8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of LangSmith, so you can see the experience inside your AI.

It does not authenticate your account with LangSmith. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

LangSmith Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_ixIJrwVWDWlC1bEOf4IyffAPgAEw302Ns6BE1oLo/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — LangSmith capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "langsmith-llm-observability-hub-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_ixIJrwVWDWlC1bEOf4IyffAPgAEw302Ns6BE1oLo/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up LangSmith in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work LangSmith owners hand off.

This MCP is built for technical teams managing production LLM applications who need to move faster than a web dashboard allows.

  • 01

    LLM Engineers

    They use the agent to debug complex traces and measure prompt performance through conversation.

  • 02

    AI Developers

    They pull the latest prompt templates from the Hub and verify dataset structures.

  • 03

    AI Analysts

    They audit human feedback queues and report on model grounding and accuracy.

FAQ

Questions LangSmith owners ask.

  • 01

    How do I connect my LangSmith data to my AI client?

    You subscribe to the MCP on Vinkius and enter your LangSmith API key and endpoint. Once connected, your AI client can immediately start querying your LangSmith data.

  • 02

    Which AI clients can use this MCP?

    This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I see specific error messages from my LLM runs?

    Yes. You can use the capability to get precise telemetry for a single run, which includes exact error strings from your AI pipelines.

  • 04

    Does this MCP host the data?

    No, this MCP connects to your existing LangSmith account. Vinkius simply hosts the connector and manages the connection so your agent can talk to LangSmith.

  • 05

    Can I manage my LangChain Hub prompts through this?

    Yes. The MCP includes capabilities to list and retrieve prompt templates and their version histories from the LangChain Hub.

  • 06

    Can I see the token usage for a specific LLM run through my agent?

    Yes. Use the get_run_telemetry capability with a specific Run ID. Your agent will retrieve the exact token count (prompt + completion) and latency metrics calculated by LangSmith for that interaction.

  • 07

    How do I fetch a prompt template from the LangChain Hub using natural language?

    The list_prompts capability allows your agent to navigate your hosted Hub repository. You can ask your agent to find a specific prompt by name to inspect its instruction text, variables, and version history.

  • 08

    Can my agent check the status of human annotation queues?

    Absolutely. Use the list_annotation_queues capability to retrieve all active queues where human feedback is being collected. Your agent can report on the number of pending traces and general alignment scores established by your reviewers.

Explore

More in Superpower

Suggestions

Connect LangSmith to Claude, Cursor, ChatGPT & more