How to Use the Cerbos MCP in LangChain

Q: Can LangChain handle complex Cerbos auth plans?

Yes, use planresources to generate query constraints. The output serves as a filter for your subsequent database operations.

Build complex authorization chains in LangChain by offloading access logic to the Cerbos 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 Cerbos MCP to LangChain

Create your Vinkius account to connect Cerbos 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 Cerbos with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chainable access control for LangChain

Feed your agent's current state directly into `authzen_evaluation` to verify user permissions before executing downstream actions. You create logic paths where access decisions dictate the next step in your chain. Because every tool result feeds into the next, you can use `plan_resources` to fetch allowed data, then pipe those IDs into your next database query. It removes the guesswork from your agent's reasoning.

Tracing Cerbos calls in LangSmith

Monitor every interaction between your LangChain agent and the Cerbos MCP server with full observability. You see exactly what inputs the agent sent to `authzen_evaluations` and how the response changed the chain's path. Latency spikes or denied requests show up in your traces immediately. Debugging becomes a matter of checking the logs rather than guessing why an agent stopped mid-task.

Persistent multi-server context

Use the client session to keep Cerbos configuration state consistent across your multi-agent pipelines. `get_authzen_config` runs once at startup, allowing your agents to focus on evaluating complex resource permissions. Statelessness is fine for simple tasks, but persistent sessions mean your LangChain agents don't re-fetch infrastructure details unnecessarily. It keeps your chains fast and your logic clean.

Setup guide

Set up Cerbos 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 Cerbos 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({
    "cerbos-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 Cerbos 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 Cerbos. 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 Cerbos 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 Cerbos MCP in LangChain

Install the MCP adapters and point your client to the server URL. You then pass the tools to your agent constructor to let it decide when to check permissions.

Yes, use `plan_resources` to generate query constraints. The output serves as a filter for your subsequent database operations.

Use the MultiServerMCPClient to aggregate Cerbos alongside your other tools. It handles the connections so your agent treats them as one toolkit.

The tool returns the denial result to your agent. You can write custom logic to catch this and pivot the agent's behavior.

Cerbos only processes your authorization policies and resource metadata. We never store your raw user data, and the server runs in an isolated sandbox for your security.

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