# Gnosem MCP server

Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.

## Links
- Registry page: https://www.getdrio.com/mcp/dev-gnosem-gnosem
- Repository: https://github.com/gnosem/gnosem
- Website: https://gnosem.dev

## Install
- Endpoint: https://gnosem.dev/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://gnosem.dev/mcp

## Tools
- memory_write - Save a fact, preference, decision, or note to the user's cross-model memory. Any MCP client can read this back later. Include written_by (e.g. 'claude-code', 'gpt-5', 'kimi-k2') for provenance and session_id to group related writes. Long content (>400 chars) is automatically compressed on write to a structured-facts form optimized for LLM reading — the raw text is preserved. Pass no_optimize:true to skip. Writes are deduped by default: (1) SHA-256 of trim(content) short-circuits byte-identical writes with { id, exact_duplicate:true } for free (no embed call); (2) failing that, semantic dedup returns { id, deduped:true, matched_score } when cosine ≥ 0.85. Pass force:true to bypass both, or use memory_supersede to explicitly correct a prior memory. Endpoint: https://gnosem.dev/mcp
- memory_search - Search the user's memories. Default mode is 'hybrid': blends semantic (cosine over Vectorize) and keyword (BM25 over SQLite FTS5) hits via Reciprocal Rank Fusion (k=60). Semantic catches paraphrases; keyword catches exact-string hits (IDs, dates, code snippets). Pass mode:'semantic' or mode:'keyword' to run just one. Content defaults to the LLM-optimized (compressed) form when available (raw:true to invert). Excludes forgotten + superseded. Optional filters narrow after retrieval: tags (AND), written_by, session_id, and/or since/until (ms epoch). Endpoint: https://gnosem.dev/mcp
- memory_list - List the user's most recent memories in reverse chronological order. Use for browsing or catching up on what the user's other model sessions have written recently. Same content/content_raw shape as memory_search. Optional filters (tags, written_by, session_id, since, until) narrow the listing at the SQL level. Endpoint: https://gnosem.dev/mcp
- memory_forget - Soft-delete a memory by id. The row is retained for audit but excluded from search/list and removed from the vector index. Endpoint: https://gnosem.dev/mcp
- memory_supersede - Replace a stale memory with a corrected one. The old row is marked superseded and excluded from future reads; the new row becomes the current version. Use for corrections; use memory_forget for pure deletions. Endpoint: https://gnosem.dev/mcp
- memory_write_bulk - Write up to 50 memories in a single call. Each entry runs the same path as memory_write (semantic dedup by default; pass force:true per-entry to skip). Embeddings + optimizations run in parallel; D1 inserts are batched. Returns { results: [...] } with one entry per input in the same order — each is { id, created_at, optimized? } on success, { id, created_at, deduped, matched_score } on dedup, or { error } on failure. Free-tier limits apply to the sum: if adding N would exceed 200, the first (200 - existing) succeed and the rest return an error. Endpoint: https://gnosem.dev/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: dev.gnosem
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 30, 2026
- Source: https://registry.modelcontextprotocol.io