Search / dev.gnosem/gnosem
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
v1.0.0 · active · repository · website · descriptor JSON · versions
protogrid{
"mcpServers": {
"gnosem": {
"type": "http",
"url": "https://gnosem.dev/mcp"
}
}
}claude mcp add --transport http gnosem https://gnosem.dev/mcp[mcp_servers.gnosem]
url = "https://gnosem.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"gnosem": {
"type": "remote",
"url": "https://gnosem.dev/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"gnosem": {
"type": "http",
"url": "https://gnosem.dev/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=gnosem&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vZ25vc2VtLmRldi9tY3AifQ%3D%3D"
}{
"servers": {
"gnosem": {
"type": "http",
"url": "https://gnosem.dev/mcp"
}
}
}{
"mcpServers": {
"gnosem": {
"httpUrl": "https://gnosem.dev/mcp"
}
}
}extensions:
"gnosem":
enabled: true
name: "gnosem"
type: streamable_http
uri: "https://gnosem.dev/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky onestools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: memory_write (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_search (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_list (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …tools.token_costabout 1,619 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changesno tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo +dns-namespace +website -unreachable(1 failures) ~updated-82d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://gnosem.dev/mcp streamable-http | none | no (1 failures) | 95% | 252 ms | 2025-06-18 | 2026-10-19 |
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. |
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. |
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). |
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. |
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. |
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. |
Schemas: list_tools.
{
"name": "dev.gnosem/gnosem",
"title": "Gnosem",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://gnosem.dev/mcp",
"type": "streamable-http"
}
],
"version": "1.0.0",
"repository": {
"url": "https://github.com/gnosem/gnosem",
"source": "github"
},
"websiteUrl": "https://gnosem.dev",
"description": "Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client."
}