What is LangSmith and why do I need it?

LangSmith is the 'Datadog for LLM applications'. Without observability, AI agents in production are black boxes — you can't see what they're doing, why they fail, or how much they cost. LangSmith traces every LLM call, chain execution, and tool use, giving you complete visibility into inputs, outputs, latency, token usage, and error rates.

Does LangSmith work only with LangChain?

No! While LangSmith is built by the LangChain team and has native LangChain/LangGraph integration, it works with any LLM application. You can trace OpenAI, Anthropic, or any LLM provider directly using the REST API. It also integrates with CrewAI, AutoGen, and other frameworks.

How much does LangSmith cost?

LangSmith offers a generous free tier with 5,000 traces per month — no credit card required. The Developer plan is $39/month with 50,000 traces. Enterprise plans include SSO, RBAC, dedicated support, and unlimited traces with volume discounts.

LangSmith MCP Server for Pydantic AI 3 tools — connect in under 2 minutes

Name: LangSmith
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 3 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect LangSmith through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to LangSmith "
            "(3 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in LangSmith?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About LangSmith MCP Server

Connect your AI agent to LangSmith — the observability platform from the LangChain team that gives you complete visibility into your LLM applications.

Pydantic AI validates every LangSmith tool response against typed schemas, catching data inconsistencies at build time. Connect 3 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

List Projects — View all tracing projects with aggregate metrics: total runs, median latency, feedback scores, and creation dates
List Runs — Browse recent traces in any project. See run names, types (LLM, chain, tool), status (success/error), token usage, and timing
Run Details — Deep-dive into any specific run to see its full execution trace, inputs, outputs, and associated feedback

The LangSmith MCP Server exposes 3 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect LangSmith to Pydantic AI via MCP

Follow these steps to integrate the LangSmith MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 3 tools from LangSmith with type-safe schemas

Why Use Pydantic AI with the LangSmith MCP Server

Pydantic AI provides unique advantages when paired with LangSmith through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your LangSmith integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your LangSmith connection logic from agent behavior for testable, maintainable code

LangSmith + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the LangSmith MCP Server delivers measurable value.

Type-safe data pipelines: query LangSmith with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple LangSmith tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query LangSmith and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock LangSmith responses and write comprehensive agent tests

LangSmith MCP Tools for Pydantic AI (3)

These 3 tools become available when you connect LangSmith to Pydantic AI via MCP:

langsmith_get_run

Useful for debugging specific LLM calls or agent actions. Get detailed information about a specific run/trace by its ID

langsmith_list_projects

Each project groups related traces together and shows aggregate metrics like total runs, median latency, and feedback counts. List all tracing projects in your LangSmith account with run counts, latency stats, and feedback metrics

langsmith_list_runs

Each run represents a single LLM call, chain execution, or agent action. Shows status (success/error), latency, and token consumption. List recent traces/runs in a specific LangSmith project. Shows run names, types, status, token usage, and timing

Example Prompts for LangSmith in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with LangSmith immediately.

"List all my LangSmith projects and show their metrics."

"Show me the last 5 runs in my production-agent project."

"Get details on the failed run a0b1c2."

Troubleshooting LangSmith MCP Server with Pydantic AI

Common issues when connecting LangSmith to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

LangSmith + Pydantic AI FAQ

Common questions about integrating LangSmith MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your LangSmith MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.