Th Memory MCP vs Cognee
A side-by-side look at the Th Memory MCP and Cognee MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Th Memory MCP 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?
Choose Th Memory MCP when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
MEMORY_DB_PATH. - You want tools like
remember, recall, get_profile.
Choose 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.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 64/100 · Good | 53/100 · Good |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | MEMORY_DB_PATH | LLM_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 3 | 33,154 |
| Directory activity | 3 views 0 installs 0 upvotes | 5 views 0 installs 0 upvotes |
| Tools | 16 | 4 |
| Full listing | View Th Memory MCP | View Cognee |
Tools & capabilities
Th Memory MCP tools 16
rememberSave or update a user preference (category+key upsert). Re-saving the same key increases confidence by 0.1 (cap 1.0). Returns the row id for forget().recallSearch preferences + lessons via full-text index, plus recent matching interactions. Use before starting a new task.get_profileGet the distilled user profile: profile sections, top preferences by confidence (max 15), and the 5 most recent lessons. Optional userId/sessionId/projectId scope the auto-projected memories; without them only GLOBAL memories are included.save_lessonRecord a lesson learned from a correction: what situation, what mistake, what is the correct way. Call immediately after the user corrects your work.search_historySearch past user prompts (kind='prompt') by keyword. Returns timestamped snippets truncated to 200 chars each.forgetDelete one memory row (preference, lesson or interaction) by id and sync the search index. Pass type when you know it (ids from remember are preference ids, from save_lesson are lesson ids).memory_statsSummarize memory usage: interaction counts by kind, preference/lesson totals, DB file size, oldest/newest interaction timestamps, and profile sections.get_recent_interactionsList recently captured raw interactions (newest first) as [id] ts [kind] content lines. Optionally filter by kind. Use for auditing history or before distilling memory.export_memoryExport preferences, lessons, profile (and optionally raw interactions) to a JSON file under data/exports/. Only writes inside that directory. Returns the file path, size in bytes and a JSON preview.get_contextAssemble relevant memories for the current task via hybrid retrieval (+ optional memory-graph expansion), with token budgeting. Use to load memory into context before a task.consolidateCluster similar memories via embedding similarity and optionally create derived/consolidated memories linked via 'derived_from'. Use during periodic consolidation.link_memoryCreate a typed relationship between two memories in the graph (supports/contradicts/supersedes/derived_from/related_to/caused_by/depends_on).- +4 more on 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 memoryrecallSearch memory with auto-routing. Searches session cache first when `session_id` is provided, then falls through to the permanent graphforgetDelete 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.
Th Memory MCP
{
"mcpServers": {
"th-memory-mcp": {
"command": "npx",
"args": [
"-y",
"th-memory-mcp"
],
"env": {
"MEMORY_DB_PATH": "YOUR_MEMORY_DB_PATH_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
Th Memory MCP 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 Th Memory MCP 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.
Th Memory MCP is listed as free. Auth: no auth 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 th-memory-mcp and topoteretes-cognee as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Th Memory MCP has a quality signal of 64/100 (Good) with 3 views, 0 installs and 3 GitHub stars. Cognee has 53/100 (Good) with 5 views, 0 installs and 33,154 GitHub stars.