How to Use the Cognee MCP in Cursor

Q: How does Cognee feed context into Cursor?

Your agent uses the cogneesearch tool through the MCP connection to query a real graph of your documentation. You get accurate code suggestions based on actual relationships instead of generic completions.

Q: Can I trigger Cognee graph updates directly from Cursor?

Yes, your agent can call cogneecognify directly from the Cursor chat or composer. This updates your knowledge base in real time.

Feed raw documents to Cursor and let your AI agent build and query a structured Cognee knowledge graph while you write code.

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 Cursor

Create your Vinkius account to connect Cognee to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Code with a live knowledge graph in Cursor

The `cognee_add_data` tool lets your editor feed raw code bases, documentation, or text assets directly into the ingestion engine. It sets up the raw data pipeline before generating the graph structure. Your coding agent uses this tool to stage context before refactoring or writing new modules. It puts an end to copy-pasting entire files into your chat window.

Build relationships with this Cognee MCP Server

The `cognee_cognify` tool processes your staged files to extract code entities, functions, and their architectural dependencies. It generates vector embeddings and maps out the entire system topology. This gives your agent a complete map of how your modules interact. It means the editor can reference exact code relationships instead of guessing.

Query your codebase architecture instantly

The `cognee_search` tool executes natural language queries against your generated graph to find architectural patterns. It traverses the nodes to pinpoint exactly where changes need to happen. You can also call `cognee_get_insights` to retrieve structured lists of system dependencies. This MCP tool feeds real-time context directly into your active coding session.

Setup guide

Set up Cognee MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Cognee MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Cognee transactions." If the MCP tools are loaded correctly, Cursor will call the Cognee tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "cognee-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Your agent uses the `cognee_search` tool through the MCP connection to query a real graph of your documentation. You get accurate code suggestions based on actual relationships instead of generic completions.

Yes, your agent can call `cognee_cognify` directly from the Cursor chat or composer. This updates your knowledge base in real time.

No, Vinkius handles the connection securely. You configure the server in your global configuration file using a single endpoint token.

Not at all. The heavy graph processing and embedding generation happen on the Vinkius infrastructure, keeping your local editor fast.

All code files, text assets, and generated graph relationships are processed in isolated, ephemeral V8 sandboxes. Your proprietary engineering data is never stored permanently or used for training.

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