Gnosem MCP server

• Registry namedev.gnosem/gnosemverified in the MCP registry

The registry name sits under gnosem.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-26
• Tools6
• Server calls itselfgnosem
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 47 ms.

• Its tools do every use case we checked: save preferences once and reuse them across assistants; search stored memories by meaning; replace outdated memories with corrected versions.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer70 ms
• Space in an agent's context≈ 1,681 tokensthe definitions of all its tools (6), which an agent carries on every turn
• Tool definitionsB · 81 of 100
• Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 1 of 6
• Not saying whether it only reads or can destroy: 6 of 6

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• 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…

• 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…

• 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…

• 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_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_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…