Central Intelligence vs Cognee

A side-by-side look at the Central Intelligence and Cognee MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Central Intelligence logoCentral IntelligenceKnowledge & Memory · Local subprocess (stdio)Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.51GoodAuth: api key requiredCognee logoCogneeKnowledge & MemoryMemory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources48FairAuth: no auth required

Verdict: choose Central Intelligence for knowledge & memory work as a local process; choose Cognee for knowledge & memory. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Central Intelligence logoChoose Central Intelligence when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You have the keys it needs: CI_API_KEY.
Explore Central Intelligence

Cognee logoChoose Cognee when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • Its auth model fits you: No auth required.
  • You have the keys it needs: LLM_API_KEY.
Explore Cognee

Feature & specification comparison

Rows where the two servers differ are marked.

SpecCentral Intelligence logoCentral IntelligenceCognee logoCognee
CategoryKnowledge & MemoryKnowledge & Memory
Quality signal51/100 · Good48/100 · Fair
Install commandConfirmedNot confirmed yet
TransportLocal subprocess (stdio)—
AuthAPI key requiredNo auth required
PricingFreemiumFree
Required env varsCI_API_KEYLLM_API_KEY
Verified ownerCommunity listingCommunity listing
GitHub stars332,581
Directory activity 3 views 0 installs 0 upvotes 5 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Central Intelligence tools

No tool names declared yet. Check the project README from the listing page.

Cognee tools

No tool names declared yet. Check the project README from the listing page.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Central Intelligence

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "alekseimarchenko-central-intelligence": {
      "command": "npx",
      "args": [
        "-y",
        "central-intelligence-local"
      ],
      "env": {
        "CI_API_KEY": "YOUR_CI_API_KEY_HERE"
      }
    }
  }
}

Cognee

No confirmed install command for Cognee yet — follow the setup steps linked from its listing page rather than a guessed package name.

Frequently asked questions

Central Intelligence is categorized under Knowledge & Memory and uses a local stdio subprocess. Cognee belongs to Knowledge & Memory and uses an install path we have not confirmed yet. Pick Central Intelligence for knowledge & memory work and Cognee for knowledge & memory.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Cognee has no confirmed install command yet — follow its own setup instructions.

Central Intelligence is listed as freemium — a free tier with paid plans. Auth: api key required. Cognee is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add alekseimarchenko-central-intelligence and topoteretes-cognee as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Central Intelligence has a quality signal of 51/100 (Good) with 3 views, 0 installs and 3 GitHub stars. Cognee has 48/100 (Fair) with 5 views, 0 installs and 32,581 GitHub stars.