How to Use the Baseten MCP in LangChain

Q: How do I connect the Baseten MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. You initialize a MultiServerMCPClient with your Vinkius endpoint token, then call client.gettools() to pass the functions into your agent.

Build multi-step reasoning chains in LangChain that query Baseten models and run inference predictions dynamically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to LangChain

Create your Vinkius account to connect Baseten to LangChain 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 Baseten with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

LangChain ReAct Agents for Baseten MCP Server

Your agent calls `list_models` and `get_model` to discover available endpoints before routing traffic. LangChain ReAct agents thrive on this kind of dynamic discovery. They'll read the configurations and pick the exact one that fits the prompt. You get full observability through LangSmith tracing during these decisions. If the agent picks the wrong model, you check the trace to see exactly what context it had. This turns black-box model routing into a clear, debuggable chain of thought.

Dynamic Inference Pipelines

The `predict` MCP tool lets your chain send tensor shapes or dictionary payloads directly to a running instance. Instead of hardcoding API calls, your agent figures out the exact payload on the fly based on previous steps. Output from one inference becomes input for the next. You might run a vision model first, take the bounding boxes, and feed them into a text summarization model. The framework handles the state transfer between these serverless predictions automatically.

Deployment Auditing Chains

Developers use `list_deployments` and `get_deployment` via this MCP Server to build automated health check pipelines. The agent grabs the active inference bounds and compares them against your target metrics. Add `list_secrets` to verify workspace configurations without exposing the actual values. This means you run security audits on your infrastructure via an automated script, logging the results straight to your internal tracking tools.

Setup guide

Set up Baseten MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Baseten tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "baseten-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Baseten transactions"
    })
    print(result["messages"][-1].content)

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 Baseten. 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 Baseten 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 Baseten MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. You initialize a `MultiServerMCPClient` with your Vinkius endpoint token, then call `client.get_tools()` to pass the functions into your agent.

Yes, they handle this natively. By giving the agent access to the model listing tools, it evaluates the options and routes the request based on the task.

Use LangSmith. Every prediction request logs latency, token usage, and the exact input payloads. You see exactly what the agent sent to the endpoint.

It does. While the connection is stateless by default, you call `client.session()` to keep context alive across multiple inference requests.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. The agent only sees metadata like tensor shapes and secret names, never the raw secret values. Once the chain finishes, the environment spins down immediately.

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