# Gnosismemory Memory MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.gnosismemory%2Fmemory
Registry id: `mcp-registry/com.gnosismemory/memory`
Status: live (checked 2026-11-22T15:00:23.094Z)

## Verdict

Gnosismemory Memory MCP server answered 100% of Glimind's liveness checks over 30 days, better than 43% of MCP servers, with 170 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (90/100) across 21 tools, costing an agent about 7,714 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 43% of MCP servers |
| Median handshake latency | 170 ms | 64% of MCP servers |
| p95 handshake latency | 388 ms | — |
| Checks in 30 days | 4,037 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 90/100 (A) | 60% of MCP servers |
| Tools | 21 | — |
| Tool-list size for an agent | ~7,714 tokens | 24% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "gnosismemory-memory-mcp-server": {
      "type": "http",
      "url": "https://gnosismemory.com"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http gnosismemory-memory-mcp-server https://gnosismemory.com
```

## Tools (21)

- `account`: Account state + billing. Returns URLs only -- user clicks to pay; never charges silently. Pick by intent: "what plan am I on?" -> info (tier, subscription, capa
- `agent_manage`: Manage agents (NAMESPACES under your account, sharing your token). An agent is a namespace, never a holder of key material: all crypto is the ACCOUNT's, and an 
- `artifact_delete`: Delete an artifact: every revision and its pointer memory. Permanent. confirm must equal the artifact name. memory_delete refuses a pointer; use this.
- `artifact_history`: List the revisions of an artifact (rev_id, parent, seq, time, author, pinned) and its heads. conflict=true means divergent heads to merge.
- `artifact_orphans`: List artifact revisions whose pointer memory is gone (a delete on one replica racing a save on another). Nothing is auto-deleted; export includes them.
- `artifact_pin`: Pin a revision so retention thinning never removes it (pinned=false unpins).
- `artifact_read`: Read an artifact by its pointer memory id (memory_retrieve on a pointer shows an "artifact" block with head_rev_id and outline). Bodies over 40,000 characters r
- `artifact_write`: Store or update a long document (markdown, JSON or text) behind a pointer memory. For agents.md, skills.md, assertions.md, a project plan: anything past one mem
- `collection_manage`: Manage shared collections (multi-user memory folders). list: your collections + invites. create. update: rename (display only; slug/keys unchanged). delete: own
- `init_core_memories`: Run ONCE at conversation start. Loads behavioral prefs + recent context. Previews carry a 'complete' flag: true = full content shown; false = opening only, memo
- `memory_add`: Store a memory. Several memories in one call -> memories=[{content, topics, ...}]; top-level topics then apply to every item. BEFORE params decide: (1) TYPE? (2
- `memory_add_batch`: Store multiple memories at once. Same rules as memory_add, applied per item. SHAPE: one ITEM here == one memory_add call. Same field names, same meaning. The ON
- `memory_consolidate`: Create/replace a topic's executive summary. One per topic; replacing archives the old (restorable). WARNING: a bad summary poisons every future session. Do NOT 
- `memory_deep_search`: Broad search for a FULL sweep -- every hit on a topic (e.g. before memory_consolidate), not a conversational lookup (that is memory_search). Up to 128 results; 
- `memory_delete`: Delete memories by ID. Permanent. memory_delete(["id1","id2"]). Delete by filter: memory_search first, collect ids, then delete.
- `memory_edit`: Edit a memory. Provide only what changes; omitted fields untouched. Modes: 1. Content replace (content [+topics/macro_topics]): full rewrite, re-embeds. Do it t
- `memory_retrieve`: Get full content by ID. Use when search returned complete=false. Batch: memory_retrieve(["id1","id2"]). Skip if complete=true (preview is already full).
- `memory_search`: 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
- `message`: Direct inter-agent text that DIES ON ACK. Use for receipts, FYIs and short replies; use signal to point at a memory. send/check/ack. LOSABLE BY DESIGN: the firs
- `signal`: Inter-agent signals -- sticky notes pointing at a memory_id. Both parties must share a collection. send: post to a teammate. check: read pending (removes nothin
- `task_feed`: Recently-changed tasks, chronological (not ranked). For "what needs attention?" / "what changed?". Find tasks by content -> memory_search. Each: preview, progre

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
