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

Q: Can my Google ADK agent filter which LangSmith tools it exposes?

Yes. You can use the optional toolnames filter in the toolset configuration. This lets you expose listruns while hiding listprompts if your agent only needs telemetry data from the MCP endpoint.

Bring LangSmith (LLM Observability & Hub) into the Google ADK to let your Gemini agents audit prompt templates and analyze trace datasets.

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 Google ADK

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze evaluation datasets

The `list_datasets` tool exposes all evaluation and fine-tuning datasets mapped in LangSmith to your Gemini agent. Your agent reads these datasets and can immediately cross-reference the results with your enterprise data sitting in BigQuery. When human review is required, the agent calls `list_annotation_queues`. It checks the active human-in-the-loop annotation queues to see which Vertex AI pipeline outputs still need manual grading.

Feed long-context agents with this MCP Server

The `list_runs` tool isolates the raw interactions containing prompts sent to and responses received from the AI models. Your Google ADK agent pulls hundreds of these runs at once, feeding them directly into Gemini's massive million-token context window. For deep debugging, the agent triggers `get_run`. This grabs the precise telemetry for a single LLM invocation run, allowing the agent to pinpoint exactly where a complex chain broke down.

Audit enterprise prompt templates

The `list_projects` tool maps out the boundaries of distinct AI pipelines currently monitored by LangSmith. The agent uses this map to navigate your different cloud environments and testing stages. From there, it uses `list_prompts` to extract prompt templates hosted in the LangChain Hub. Your agent reads the exact instructions your models rely on, ensuring they comply with your internal deployment standards.

Setup guide

Set up LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) 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 (LLM Observability & Hub)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LangSmith (LLM Observability & Hub) 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 (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 Google ADK

Install the google-adk package. Configure an McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset to your LlmAgent under the tools argument.

Yes. You can use the optional tool_names filter in the toolset configuration. This lets you expose list_runs while hiding list_prompts if your agent only needs telemetry data from the MCP endpoint.

It connects your Gemini agents directly to your tracing infrastructure. You can pull massive amounts of run data into Gemini's long context window to automatically diagnose pipeline failures.

Yes. The Google ADK supports both transport layers natively. Vinkius provides the HTTP endpoint, so you just drop the URL into the server parameters.

Your agent accesses raw interactions containing prompts sent to and responses received from the models. Vinkius manages the MCP connection via an ephemeral V8 sandbox that drops all state immediately after the request. You only need one endpoint token, keeping your LangSmith credentials isolated from the client application.

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