Throughline vs Cognee

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

T
ThroughlineKnowledge & Memory
A persistent AI self you own — memory, persona, judgment — portable across all your AI hosts.37FairAuth: not declared
Cognee logoCogneeKnowledge & MemoryMemory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources53GoodAuth: no auth required

Verdict: choose Throughline for knowledge & memory work; choose Cognee for knowledge & memory. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

T
Choose Throughline when

  • You need dedicated capabilities in the Knowledge & Memory domain.
Explore Throughline

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.
  • You want tools like remember, recall, forget.
Explore Cognee

Feature & specification comparison

Rows where the two servers differ are marked.

Spec
T
Throughline
Cognee logoCognee
CategoryKnowledge & MemoryKnowledge & Memory
Quality signal37/100 · Fair53/100 · Good
Install commandNot confirmed yetNot confirmed yet
Transport——
AuthNot declaredNo auth required
PricingNot declaredFree
Required env varsNone listedLLM_API_KEY
Verified ownerCommunity listingCommunity listing
GitHub stars—32,674
Directory activity 0 views 0 installs 0 upvotes 5 views 0 installs 0 upvotes
ToolsNot listed4

Tools & capabilities

Throughline tools

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

Cognee tools 4

  • rememberStore data in memory. Pass `data` for text, or `filename` + `content_base64` to ingest an uploaded file (up to 10 MB). With `session_id`: fast session cache (text only). Without `session_id`: permanent graph memory
  • recallSearch memory with auto-routing. Searches session cache first when `session_id` is provided, then falls through to the permanent graph
  • forgetDelete memory by dataset name or id, a single data item by `data_id` (paired with its `dataset_id`, both shown by `recall` with `include_references=True`), or delete all owned memory with `everything=True`
  • cognify_statusCheck the progress of background ingestion started by `remember(background=True)`. Unadvertised by default; discoverable via `search_tools` and callable by name

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.

Throughline

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

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

Throughline is categorized under Knowledge & Memory and uses an install path we have not confirmed yet. Cognee belongs to Knowledge & Memory and uses an install path we have not confirmed yet. Pick Throughline for knowledge & memory work and Cognee for knowledge & memory.

Neither server has a confirmed install command yet, so we don't publish a guessed config. Follow each project's own setup instructions, linked from its listing page.

Throughline has no declared pricing — check the project's own site. 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 throughline and topoteretes-cognee as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Throughline has a quality signal of 37/100 (Fair) with 0 views, 0 installs and 0 GitHub stars. Cognee has 53/100 (Good) with 5 views, 0 installs and 32,674 GitHub stars.