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

Q: How can a CrewAI agent access traces in LangSmith (LLM Observability & Hub) using an MCP Server?

You pass the MCP Server URL to your CrewAI agent's mcps list, granting it access to listruns. The agent can then fetch and analyze its own execution traces or those of other crew members.

Q: Can CrewAI agents pull their task descriptions from LangSmith (LLM Observability & Hub)?

Yes. The listprompts tool allows your CrewAI agents to load their roles and task templates dynamically from the Hub, keeping your Python agent definitions clean and decoupled.

Q: How do I monitor multi-agent execution paths using LangSmith (LLM Observability & Hub) in CrewAI?

The listprojects tool lets your CrewAI manager agent identify the active tracing project. It can then isolate and audit the entire multi-agent execution path using the listruns tool.

Equip your CrewAI agent teams with LangSmith tools to audit their own traces and pull prompt templates.

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 CrewAI

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let CrewAI supervisor agents audit multi-agent traces

`list_runs` gives your CrewAI supervisor agent the power to inspect the raw interactions of subordinate agents. Instead of running blind, the supervisor audits the actual prompts sent and responses received during a collaborative task. This MCP Server provides `get_run` so your agents can fetch precise telemetry on individual execution runs. If an agent produces a hallucination, the moderator agent pulls the exact trace to run a local correction cycle.

Synchronize crew prompts with the LangChain Hub

`list_prompts` allows your CrewAI agents to pull their specialized system instructions dynamically. You don't have to hardcode agent descriptions or tasks inside your Python scripts; instead, agents fetch their updated roles directly from your central hub. This integration ensures that your multi-agent team always executes tasks using the latest tested prompt templates. Your developers can optimize prompt variables in the cloud while the crew runs autonomously on your local machine.

Map agent execution boundaries across distinct projects

`list_projects` maps out the active tracing boundaries for your different agent crews. Your manager agent uses this tool to ensure that telemetry from a research crew doesn't mix with the logs of a separate engineering crew. By using `list_datasets`, your crew can also pull gold-standard evaluation datasets into their shared memory. This allows a QA agent within the crew to run automated checks against your production test suites.

Setup guide

Set up LangSmith (LLM Observability & Hub) MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke LangSmith (LLM Observability & Hub) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="LangSmith (LLM Observability & Hub) Analyst",
    goal="Access and analyze LangSmith (LLM Observability & Hub) data via MCP.",
    backstory="Expert analyst with direct LangSmith (LLM Observability & Hub) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent LangSmith (LLM Observability & Hub) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="LangSmith (LLM Observability & Hub) Analyst",
        goal="Access and analyze LangSmith (LLM Observability & Hub) data via MCP.",
        backstory="Expert analyst with direct LangSmith (LLM Observability & Hub) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent LangSmith (LLM Observability & Hub) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the MCP Server URL to your CrewAI agent's `mcps` list, granting it access to `list_runs`. The agent can then fetch and analyze its own execution traces or those of other crew members.

Yes. The `list_prompts` tool allows your CrewAI agents to load their roles and task templates dynamically from the Hub, keeping your Python agent definitions clean and decoupled.

The `list_projects` tool lets your CrewAI manager agent identify the active tracing project. It can then isolate and audit the entire multi-agent execution path using the `list_runs` tool.

You can register this MCP Server by passing the Vinkius HTTP URL directly into the agent's `mcps` parameter during initialization. For more control, use the `MCPServerHTTP` class from `crewai.mcp` to expose specific tools to specific agents.

No, your data is secure. All interactions with your project boundaries and raw agent inputs/outputs are secured by Vinkius's zero-trust gateway. Your API keys are handled securely, and this MCP Server ensures trace data is never stored outside your configured LangSmith endpoint.

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