MCP tool reference · #427 of 563 by publishers
memory_search
Exposed by 9 servers from 9 publishers, read from the live servers by the Serverdex check; most of them sit in AI & Agents; 77.8% of them take a query parameter; the most-starred is Synaplan (1.1k stars).
memory_search(query: string, limit?: integer, …)Parameters
share = % of the 9 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| query | string | 77.8% | 57.1% | Natural-language query describing the memory to look up. |
| limit | integer | 55.6% | 0% | 1-50, default 10. |
| mode | string | 22.2% | 0% | Retrieval mode. Default 'hybrid'. |
| q | string | 22.2% | 100% | What to look for, in natural language. |
| session_id | string | 22.2% | 0% | Only return memories with an exact session_id match. |
| since | integer | 22.2% | 0% | Only return memories created at or after this ms-epoch timestamp. |
| tags | array | 22.2% | 0% | Only memories having ALL of these tags. |
| until | integer | 22.2% | 0% | Only return memories created strictly before this ms-epoch timestamp. |
| agent_token | string | 11.1% | 0% | — |
| agents | string | 11.1% | 0% | — |
| as_of | string | 11.1% | 0% | ISO-8601 instant; search memory as it stood then. |
| budget_tokens | integer | 11.1% | 0% | — |
Source: the input schema each server returns for memory_search, aggregated over the 9 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with memory_search
9 of 9 · 9 publishers · 9 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes memory_search |
|---|---|---|---|---|---|---|
| 1 | Synaplanmetadist · AI & Agents | metadist | AI & Agents | 1.1k | yes | Search the authenticated user's stored long-term memories (preferences, facts, context) using semantic similarity. |
| 2 | Bentodzhng · Media & Creative | dzhng | Media & Creative | 1 | yes | Search durable memory records by relevance. |
| 3 | The Commons by Dead Brands, LLC — Live Gamesdstrausser83 · Games & Sports | dstrausser83 | Games & Sports | — | yes | memory_search. WHEN: find notes by text/tag (newest first). Differs from memory_get / memory_read (exact key) and memory_list (no query). Optional scope=rivalry|project|area searches that shared notebook (scope=bot or omitted = your private notes). Returns total, has_more, and next_cursor; pass cursor to page. Example: memory_search {} |
| 4 | AIfa Memorymaksimgalatin · AI & Agents | maksimgalatin | AI & Agents | — | yes | Search the user's AIfa memory by meaning: every conversation they had with AIfa on aifa.works, codeofdigitaleternity.com, aifa.digital and radiocode.space, plus notes saved by agents. Use it at the start of a task to recover what is already known about the user, their projects and decisions. |
| 5 | Wicked MCPwickedapi · Finance | wickedapi | Finance | — | yes | [Wicked Memory] Semantic search over YOUR memories only, ranked by real cosine similarity. The one metered call: free with MEMORY_API_KEY, otherwise http_status 402 with x402 v2 instructions under `payment_required` (0.001 USDC on Base) — pay, then call again with the SAME arguments (a 402 does not consume the nonce) plus payment_signature. Use when you want to recall your memories by meaning rat |
| 6 | Marsellmarsell-official · Other | marsell-official | Other | — | yes | Searches what Marsell remembers about the business: facts (its name, site, description, audience, voice, whose accounts posts come from, the facts the owner confirmed and the owner's answers), the owner's own rules and preferences (these always win), and the active learnings the planning passes wrote, each with its confidence, when it was last confirmed and how much evidence backs it. Use it befor |
| 7 | SKV Networkskv-neteork · AI & Agents | skv-neteork | AI & Agents | — | yes | Search the event, not the question (date/since/until). Suggest when: the user asks what was said, or about another agent; pass lines=all. [C v5.66286e:H,R02,R05m] |
| 8 | Gnosemgnosem · AI & Agents | gnosem | AI & Agents | — | yes | 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 |
| 9 | Gnosis Memorytekgnosis · AI & Agents | tekgnosis | AI & Agents | — | yes | Search memories by relevance. Up to 32 results. Query = ALL nouns from the user's message, not just the main one (ranking is automatic). "How does the app cache API calls?" -> "app cache api calls" complete=false results are truncated -> memory_retrieve(id) for full content. Auto-includes all your shared collections (fan-out). |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.