How to Use the LangSmith (LLM Observability & Hub) MCP in Claude Code

Q: Can Claude Code grab prompt templates from LangSmith (LLM Observability & Hub)?

Yes, Claude Code uses the listprompts tool to pull active templates from the hub. It can display the template content or save it to a local file for further terminal processing.

Q: How do I add this MCP Server for LangSmith (LLM Observability & Hub) to my Claude Code configuration?

Run the command claude mcp add --transport http langsmith -- in your terminal. Claude Code will write the configuration to your local /.claude.json file and instantly activate the tools.

Q: Can I view active annotation queues using the CLI?

Yes, the listannotationqueues tool allows Claude Code to list your active review queues. This lets you check queue depths and review statuses directly from your shell.

Inspect LLM traces and audit prompt templates directly from your terminal using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LangSmith (LLM Observability & Hub) MCP to Claude Code

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup LangSmith (LLM Observability & Hub) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query run telemetry from the command line

The `list_runs` tool isolates the raw interactions containing prompts sent to and responses received from the AI models directly inside your shell. Claude Code uses this MCP Server to pipe recent production traces into terminal outputs, letting you audit application behavior without a browser. It is the fastest way to check what your production models are actually outputting. To drill down, Claude Code calls `get_run` to get precise telemetry for a single LLM invocation run. This returns execution latency, token usage, and exact error messages directly to your terminal. You can easily script this to flag high-latency runs or trigger automated alerts in your CI/CD pipelines.

Manage prompts with Claude Code MCP Server

The `list_prompts` tool extracts prompt templates hosted in the LangChain Hub right into your terminal session. Our CLI agent uses this to quickly print, diff, or test active templates without leaving the command line. It keeps your terminal-centric workflow fast and distraction-free. It pairs this with `list_projects` to map out the boundaries of distinct AI pipelines currently monitored by LangSmith. This allows you to verify which project is receiving traces and ensure your CLI environment is configured correctly before running integration tests.

Track datasets and review queues from the CLI

The `list_datasets` tool lists all evaluation and fine-tuning datasets mapped in LangSmith for quick terminal inspection. Claude Code queries this list to find active evaluation sets, making it easy to reference test data when writing shell scripts. You can quickly see which datasets are available for your testing runs. For team workflows, the agent calls `list_annotation_queues` to list active human-in-the-loop annotation queues. This lets you monitor human review backlogs directly from your command line interface. It helps SREs and developers keep tabs on queue sizes without opening a heavy web application.

Setup guide

Set up LangSmith (LLM Observability & Hub) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see langsmith-llm-observability-hub-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest LangSmith (LLM Observability & Hub) transactions." It will automatically discover and invoke the available LangSmith (LLM Observability & Hub) tools.

Terminal

claude mcp add --transport http langsmith-llm-observability-hub-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the LangSmith (LLM Observability & Hub) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "langsmith-llm-observability-hub-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by LangSmith. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect LangSmith (LLM Observability & Hub) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about LangSmith (LLM Observability & Hub) MCP in Claude Code

You can ask Claude Code to inspect recent runs, and it will use the `list_runs` tool to grab the trace list. From there, it uses `get_run` to display detailed latency, token counts, and error states directly in your terminal.

Yes, Claude Code uses the `list_prompts` tool to pull active templates from the hub. It can display the template content or save it to a local file for further terminal processing.

Run the command `claude mcp add --transport http langsmith -- ` in your terminal. Claude Code will write the configuration to your local `~/.claude.json` file and instantly activate the tools.

Yes, the `list_annotation_queues` tool allows Claude Code to list your active review queues. This lets you check queue depths and review statuses directly from your shell.

All trace payloads, dataset rows, and prompt templates are processed in memory within Vinkius's secure, ephemeral MCP sandbox. The connection uses HTTPS to fetch data directly from LangSmith, ensuring your proprietary LLM data is never leaked or stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript