mcp server
Gnosem
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
Description as published by the maintainer. Source
- version 1.0.0
- active
- memory and context
active — Most recent push to the repository was 2026-07-30. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
6 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
memory_forget(id)- Soft-delete a memory by id. The row is retained for audit but excluded from search/list and removed from the vector index. Required: id.
memory_list(raw, tags, limit, since, until, cursor, session_id, written_by)- 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.
memory_search(k, raw, mode, tags, query, since, until, session_id, written_by)- 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 Excludes forgotten + superseded.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). Required: query.
memory_supersede(tags, old_id, session_id, written_by, new_content)- 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 The old row is marked superseded and excluded from future reads; the new row becomes the current version.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. Required: old_id, new_content.
memory_write(tags, force, content, session_id, written_by, no_optimize)- 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. Required: content.
memory_write_bulk(memories)- 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. Required: memories.
Last successful function declaration observed on . Source: https://gnosem.dev/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://gnosem.dev/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 0 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-30 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-30 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-30 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 6 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | gnosem.dev | |
| mcp endpoint status | ok | The server listed 6 functions when asked. | as of probe | gnosem.dev |
Where to get it
Related, by what their authors tagged them
-
Flarelink
— last commit 2026-06-17, shares d1
Build on the Flarelink stack — Cloudflare auth, D1, and R2 — from your AI coding tools.
-
Flarelink
— last commit 2026-06-17, shares d1
Build on the Flarelink stack — Cloudflare auth, D1, and R2 — from your AI coding tools.
-
refd
— last commit 2026-07-30, shares chatgpt, cloudflare-workers
Read AI search visibility, competitors, citations, prompts, and answer evidence from refd.
-
Flaim Fantasy
— last commit 2026-08-06, shares chatgpt, cloudflare-workers
Read-only fantasy analysis for ESPN, Yahoo, and Sleeper leagues via MCP
-
DigestSEO AI Visibility
— last commit 2026-07-27, shares chatgpt, cloudflare-workers
Track how ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews cite your brand.
-
DigestSEO mcp-geo — AI Visibility MCP Server
— last commit 2026-07-27, shares chatgpt, cloudflare-workers
DigestSEO mcp-geo: track brand citations across five AI search engines.
-
Amber
— last commit 2026-06-15, shares ai-memory, chatgpt
Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.
-
io.github.bobybarack/sovseal-memory
— last commit 2026-08-05, shares ai-memory, chatgpt
Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.
-
io.github.darknodebros/elesync
— last commit 2026-08-05, shares ai-memory, chatgpt
Local-first MCP memory vault: files you own, shared across ChatGPT, Claude, Gemini & any MCP client
-
io.github.hifriendbot/cogmemai
— shares ai-memory, chatgpt
95.10% LongMemEval (highest published). Encrypted persistent memory for Ai coding assistants.
These share tags the maintainers applied themselves, such as d1, chatgpt, cloudflare-workers, ai-memory. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: ai, ai-memory, chatgpt, claude, cloudflare-workers, d1, llm-tools, mcp, model-context-protocol, vectorize.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json