How to Use the LangSmith MCP in Google ADK

Q: Can a Google ADK agent filter LangSmith projects by latency?

Yes, your agent can execute langsmithlistprojects to pull median latency stats. This helps identify which environments are running slowly.

Q: Can I restrict which tools the agent can access?

Yes, you can use the optional toolnames filter during toolset initialization. This restricts the agent to specific commands.

Connect your Google ADK agents to LangSmith to track token metrics via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LangSmith MCP to Google ADK

Create your Vinkius account to connect LangSmith to Google ADK 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 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug Google ADK Agents with Telemetry

Gemini models handle massive token contexts, but tracking costs and latency in enterprise pipelines is tough. This MCP Server gives your Google ADK agent direct access to execution telemetry so you can monitor expensive runs. By using `langsmith_list_runs`, your agent pulls token usage and timing details for any past execution. This lets you inspect high-context runs to see if they are actually returning useful data or just burning budget.

Monitor Large-Scale Tracing Projects

When you hook your agent to BigQuery data, you need to verify that queries execute efficiently. Grouping these operations into projects keeps your enterprise pipeline organized. Use `langsmith_list_projects` to get aggregate latency statistics and run counts. It gives your team a high-level view of how Gemini interacts with your Google Cloud data sources.

Inspect Gemini Trace Details

When an agentic workflow fails, you need the raw payload of the specific step that broke. Waiting for logs to propagate through cloud consoles takes too long. Call `langsmith_get_run` to retrieve the exact execution trace of the failing agent step. This lets you debug prompt issues or model drift without leaving your development environment.

Setup guide

Set up LangSmith MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with LangSmith tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="LangSmith_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LangSmith tools via MCP.",
    tools=mcp_tools,
)

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 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 MCP in Google ADK

Initialize McpToolset with your HTTP server parameters and pass it to the LlmAgent tools list. This MCP integration lets your agent immediately call `langsmith_list_runs` to monitor execution traces.

Yes, your agent can execute `langsmith_list_projects` to pull median latency stats. This helps identify which environments are running slowly.

Absolutely. When Gemini processes large payloads, you can use `langsmith_get_run` to inspect token counts. This verifies how much of the context window was consumed.

Yes, you can use the optional tool_names filter during toolset initialization. This restricts the agent to specific commands.

All communications with the LangSmith API are encrypted in transit. The MCP Server only handles your run names, token counts, and latencies inside ephemeral sandboxes, ensuring your proprietary prompts never get leaked or saved.

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