Skip to main content
The Integrations page (route /integrations, under the CONNECT section of the sidebar alongside API Keys) is the in-product hub for wiring external tools into your Cognee memory. Each card opens a step-by-step modal that injects your tenant’s live base URL and API key into copy-on-click code blocks, so the snippets are ready to paste without editing. Everything in these flows runs locally on your machine — nothing is sent to Cognee. When a step writes to an existing config file, the previous version is backed up to .bak before being overwritten. The page has three sections, in order: Agents (“Connect your AI agents and coding tools to Cognee for persistent memory”), Automation platforms (“Give your automation workflows access to Cognee memory via MCP”), and Data sources (marked Coming soon).

​
Agents

Agent cards come in two styles depending on how the tool reads memory.

​
Prompt-based

These cards (CTA Connect via prompts) write a memory instruction file into your project or workspace so the agent learns to use Cognee through its system prompt:
ToolFile written
Claude CodeCLAUDE.md
CodexAGENTS.md
OpenClaw~/.openclaw/workspace/AGENTS.md
Prompt-based flows read the COGNEE_BASE_URL environment variable. The instruction file teaches the agent to recall context before answering and to remember new facts afterward. For Claude Code you can also install the marketplace plugin, which adds Cognee memory commands: 
/plugin marketplace add topoteretes/cognee-integrations
/plugin install cognee-memory@cognee

​
MCP-based

These cards (CTA Connect via MCP) register Cognee as an MCP server in the client’s config. First install the server: 
pip install cognee-mcp
The server command is cognee-mcp. The flow writes a stdio entry shaped like this: 
{
  "mcpServers": {
    "cognee": {
      "command": "cognee-mcp",
      "env": {
        "COGNEE_SERVICE_URL": "https://your-tenant.aws.cognee.ai",
        "COGNEE_API_KEY": "your-api-key"
      }
    }
  }
}
Each client reads its config from a different location:
ClientConfig location
Claude Desktop$HOME/Library/Application Support/Claude/claude_desktop_config.json
Cursor~/.cursor/mcp.json
Hermes Agent~/.hermes/config.yaml (YAML)
VS Code.vscode/mcp.json (Copilot agent mode)
Gemini CLI~/.gemini/settings.json
ClineVS Code Cline sidebar → MCP Servers
For VS Code, the key is supplied via an input prompt and kept out of the committed config file.

​
API / MCP

The Connect via API or MCP card is for any tool not covered above. It gives you a curl recall example and the option to install the generic Cognee skill: 
curl -X POST https://your-tenant.aws.cognee.ai/api/v1/recall \
  -H "X-Api-Key: $COGNEE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "What do you know from cognee?"}'

​
Automation platforms

Bring Cognee memory into your workflow tools (CTA Connect via node / Connect via plugin):
PlatformHow
n8nInstall the community node package n8n-nodes-cognee, then add a Cognee API credential.
DifyInstall the Marketplace plugin by topoteretes.
For Dify, the base URL must include the /api suffix (for example https://your-tenant.aws.cognee.ai/api).

​
Credentials and environment variables

The flows export three variables together. Which one a tool reads depends on how it was built:
VariableUsed by
COGNEE_BASE_URLPrompts and skills
COGNEE_SERVICE_URLPlugins and MCP servers — if missing, the client drops into local mode
COGNEE_API_KEYAll clients, for authentication
Authentication uses the X-Api-Key header (not Bearer). To confirm a key and URL work, run a health ping against the datasets endpoint: 
curl https://your-tenant.aws.cognee.ai/api/v1/datasets/ \
  -H "X-Api-Key: $COGNEE_API_KEY"
A 200 means the connection is good, 401 means the key is wrong, and 404 or a 5xx means the URL is wrong or the service is unavailable.

​
How memory works once connected

Connected tools read and write memory through two endpoints. Recall (POST /api/v1/recall) retrieves context. The search_type parameter controls how results are assembled:
search_typeBehavior
HYBRID_COMPLETIONDefault — combines graph and chunk retrieval.
GRAPH_COMPLETIONAnswers from the knowledge graph.
CHUNKSReturns raw matching text chunks.
GRAPH_SUMMARY_COMPLETIONSummarized graph-based answer.
Remember (POST /api/v1/remember/entry) stores a fact. Tie related entries together with a shared session_id: 
{
  "entry": { "type": "qa", "question": "...", "answer": "..." },
  "dataset_name": "default_dataset",
  "session_id": "..."
}
The default dataset name is default_dataset.
Use /remember/entry for inline text. The plain /remember endpoint requires a file upload and returns 422 for inline text.

​
Verify the connection

After running any flow, verify the integration by asking the connected agent:
What do you know from cognee?
If memory is wired up correctly, the agent recalls context from your knowledge graph. The final step of each flow includes a Go to Sessions → button that takes you to your live Sessions.

​
Data sources

The Data sources section is marked Coming soon. These cards are disabled today and show a Notify me button:
  • Slack
  • Notion
  • Google Drive
  • Google Drive Sheets
  • GitHub
  • Linear
  • Confluence
  • Jira
To request another source, email support@cognee.ai.

Sessions

Inspect the live memory your connected tools read and write.

API Keys

Create and manage the keys these integrations authenticate with.

Cloud SDK

Call recall and remember programmatically from your own code.

Cloud MCP

Details on the Cognee MCP server and its tools.