How is Cognee different from standard RAG?

Standard RAG splits documents into chunks and finds similar text using vector search — but it loses the relationships between facts. Cognee builds a knowledge graph that preserves entity relationships, temporal connections, and hierarchical structures. When you search, Cognee uses graph traversal combined with vector similarity and LLM reasoning, resulting in more accurate, context-aware answers that understand HOW facts relate to each other.

What search types are available?

Cognee supports four retrieval strategies: GRAPH_COMPLETION (default — combines vector search + graph traversal + LLM reasoning for context-aware answers), SUMMARIES (fast hierarchical overview search), INSIGHTS (structured entity relationships), and CHUNKS (pure vector similarity for raw text passages). Each strategy optimizes for different use cases.

Is Cognee open-source?

Yes! Cognee is fully open-source under the Apache 2.0 license. You can self-host the entire platform including the knowledge graph engine, vector database, and API server. A managed cloud version with API keys is also available for teams that prefer not to manage infrastructure.

Cognee MCP Server for Claude Code 4 tools — connect in under 2 minutes

Name: Cognee
Availability: InStock
Author: Vinkius

docs.anthropic.com/en/docs/claude-code

Built by Vinkius GDPR 4 Tools CLI

Claude Code is Anthropic's agentic CLI for terminal-first development. Add Cognee as an MCP server in one command and Claude Code will discover every tool at runtime. ideal for automation pipelines, CI/CD integration, and headless workflows via Vinkius.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

RecommendedModern Approach — Zero Configuration

Vinkius Desktop App

The modern way to manage MCP Servers — no config files, no terminal commands. Install Cognee and 2,500+ MCP Servers from a single visual interface.

Download Free Open SourceNo signup required

Classic Setup·bash

# Your Vinkius token. get it at cloud.vinkius.com
claude mcp add cognee --transport http "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Cognee MCP Server

Connect your AI agent to Cognee — the open-source knowledge graph platform that transforms unstructured data into structured, searchable knowledge.

Claude Code registers Cognee as an MCP server in a single terminal command. Once connected, Claude Code discovers all 4 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where Cognee data drives decisions without human intervention.

What you can do

Add Data — Ingest raw text, documents, or structured data into named datasets. Cognee processes and stores the data for subsequent graph construction
Cognify — Transform ingested data into a structured knowledge graph by automatically extracting entities, relationships, and semantic connections
Search Knowledge — Query the knowledge graph using four retrieval strategies: graph-aware completion (LLM + graph traversal), summaries, structured insights, or raw vector similarity
Get Insights — Retrieve structured entity relationships showing how concepts connect across your knowledge base

Why Cognee over standard RAG?

Relationship-aware — understands HOW facts connect, not just what they say
Graph + Vector hybrid — combines graph traversal with semantic search for superior recall
Temporal awareness — tracks when facts were added and reason over time-based connections

The Cognee MCP Server exposes 4 tools through the Vinkius. Connect it to Claude Code in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Cognee to Claude Code via MCP

Follow these steps to integrate the Cognee MCP Server with Claude Code.

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed

Add the MCP Server

Run the command above in your terminal

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session

Start using Cognee

Ask Claude: "Using Cognee, show me...". 4 tools are ready

Why Use Claude Code with the Cognee MCP Server

Claude Code provides unique advantages when paired with Cognee through the Model Context Protocol.

Single-command setup: `claude mcp add` registers the server instantly. no config files to edit or applications to restart

Terminal-native workflow means MCP tools integrate seamlessly into shell scripts, CI/CD pipelines, and automated DevOps tasks

Claude Code runs headlessly, enabling unattended batch processing using Cognee tools in cron jobs or deployment scripts

Built by the same team that created the MCP protocol, ensuring first-class compatibility and the fastest adoption of new protocol features

Cognee + Claude Code Use Cases

Practical scenarios where Claude Code combined with the Cognee MCP Server delivers measurable value.

CI/CD integration: embed Cognee tool calls in your deployment pipeline to validate configurations or fetch secrets before shipping

Headless batch processing: schedule Claude Code to query Cognee nightly and generate reports without human intervention

Shell scripting: pipe Cognee outputs into other CLI tools for data transformation, filtering, and aggregation

Infrastructure monitoring: run Claude Code in a cron job to query Cognee status endpoints and alert on anomalies

Cognee MCP Tools for Claude Code (4)

These 4 tools become available when you connect Cognee to Claude Code via MCP:

cognee_add_data

After ingestion, use the cognify tool to process the data into a structured knowledge graph with entities and relationships. Ingest text or documents into the Cognee knowledge base. This is the first step before building a knowledge graph

cognee_cognify

This step extracts entities, identifies relationships, generates embeddings, and creates the graph structure needed for intelligent search. Process ingested data into a structured knowledge graph. Extracts entities, relationships, and builds a searchable graph structure

cognee_get_insights

Useful for understanding relationships between topics, discovering hidden connections, and building comprehensive knowledge views. Retrieve structured entity relationships and insights from the knowledge graph

cognee_search

Search the knowledge graph using natural language. Returns context-aware answers using graph traversal and semantic search

Example Prompts for Cognee in Claude Code

Ready-to-use prompts you can give your Claude Code agent to start working with Cognee immediately.

"Add this research data to my knowledge base: 'Transformer models were introduced by Vaswani et al. in 2017 in the paper Attention Is All You Need. They use self-attention mechanisms and have become the foundation for models like GPT, BERT, and T5.'"

"Process my data into a knowledge graph."

"What is the relationship between Transformers and GPT?"