How to Use the Anyscale MCP in LangChain

Chain Anyscale LLM calls and job management directly inside your LangChain agents for complex reasoning pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anyscale MCP to LangChain

Create your Vinkius account to connect Anyscale 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 Anyscale with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Anyscale endpoints in LangChain

Feed the output of `chat_completion` directly into your next chain link. You gain full observability over every step using LangSmith tracing to monitor latency and token counts. This setup lets your agent decide exactly when to invoke an Anyscale tool based on intermediate results. It turns your logic into a sequence of predictable, data-driven steps.

Manage batch jobs via LangChain

Use `list_jobs` to pull your current training or batch status into your agent's context. Your chain can then trigger logic based on whether a job succeeded or failed. It removes the need for manual monitoring. You get a direct feedback loop between your infrastructure state and your agent's reasoning process.

Dynamic model selection with LangChain

Call `list_models` to see which endpoints are currently live on your cluster. Your agent can then dynamically select the right model for the specific task at hand. This prevents hard-coding model names in your chains. It keeps your pipeline flexible as you roll out new fine-tuned versions or update your Anyscale deployments.

Setup guide

Set up Anyscale 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 Anyscale 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({
    "anyscale-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 Anyscale 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 Anyscale. 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 Anyscale 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 Anyscale MCP in LangChain

Install the necessary adapters and use the MultiServerMCPClient. Point it at your Vinkius endpoint to start pulling tools directly into your agent constructor.

Yes, the architecture supports multi-server aggregation. You can combine Anyscale tools with your existing databases or vector stores in the same chain.

Vinkius handles all auth via an ephemeral endpoint token. We never store your credentials, and your data remains isolated within the V8 sandbox.

By default, the connection is stateless. You should use the client session feature if you need to keep context across multiple agent turns.

The server provides raw data through the tool outputs. You can pipe these directly into your LangSmith traces to review every detail of your job history.

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