How to Use the Cognee MCP in LangChain

Q: How do I initialize the Cognee MCP Server in my LangChain project?

Install the adapter package using pip install langchain-mcp-adapters langgraph first. Then, initialize MultiServerMCPClient with the Vinkius URL and pass the tools directly to your agent setup.

Feed raw text into LangChain chains and let your agents build local knowledge graphs on the fly with 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 Cognee MCP to LangChain

Create your Vinkius account to connect Cognee 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 Cognee with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Cognee graphs inside LangChain chains

`cognee_add_data` registers your raw text documents directly into the graph database during any step of your active chain. Your LangChain agent handles the data collection, feeds it to this tool, and instantly updates your memory store without manual pipeline hops. You get clean, structured nodes from messy raw inputs. LangSmith traces every single write, so you see exactly how much context your agent pushes into the system before triggering the next step.

Extract deep relationships using LangGraph agents

`cognee_cognify` processes your ingested raw data to extract entities, map out their relationships, and generate graph embeddings. LangGraph agents coordinate this tool call right after ingestion to build a structured, queryable map of your custom datasets. This step runs asynchronously inside your custom reasoning loop. You can monitor the execution times and token usage directly through your LangSmith dashboard to keep your graph builds fast and cheap.

Run graph-aware searches inside your MCP Server chains

`cognee_search` queries your structured knowledge graph using natural language to retrieve context-aware answers. Your LangChain agent uses this tool to traverse nodes and resolve complex queries that standard vector databases miss. Combining this search tool with other LangChain integrations lets you build smarter RAG pipelines. You get clean, structured context back, which your agent feeds into the next prompt in your chain.

Setup guide

Set up Cognee 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 Cognee 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({
    "cognee-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 Cognee 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 Cognee. 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 Cognee 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 Cognee MCP in LangChain

Install the adapter package using `pip install langchain-mcp-adapters langgraph` first. Then, initialize `MultiServerMCPClient` with the Vinkius URL and pass the tools directly to your agent setup.

Yes, you can configure your LangChain agent to trigger this tool immediately after it finishes running `cognee_add_data`. This lets the agent build the knowledge graph dynamically during execution.

Every tool execution shows up in your LangSmith dashboard automatically. You can track latency, input text, and returned graph nodes for every single call.

This tool pulls the high-level relationships and hidden connections from your graph. Your agent uses these insights to plan its next chain steps based on real connections instead of guessing.

Your raw text files and graph structures stay isolated inside Vinkius's secure sandbox environment. No data leaks to third-party model providers, keeping your proprietary graph data completely private.

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