Mneme MCP Server

Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.

Remote serverstreamable-httpPython

What is the Mneme MCP server?

Connect Mneme to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth. The mneme mcp server is what makes that connection.

What the server does

Every session starts from zero. You re-explain the same architecture, the same constraints, the same decision you already settled yesterday, and the tools that promise to fix it mostly store your conversation history in opaque SQLite blobs and call an LLM every time you finish a session. The record of your own work ends up somewhere you cannot read, cannot grep, and cannot take with you.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • mneme_search — FTS5 BM25 retrieval over the vault with Turkish casefold normalization, plus date, memory-type, and scope filters. Returns ranked hits and
  • mneme_recall — Retrieves indexed documents by session identifier, date range, and scope. Returns paths, titles, modification times, memory types, and optionally the
  • mneme_write — Atomically appends or replaces a markdown section in a vault file. Enforces vault path containment and redacts private spans before storage
  • mneme_summarize — Groups FTS5 matches for a topic by vault directory within optional date and scope filters. Graphiti enrichment appears only when that optional local
  • mneme_timeline — Returns scope-restricted references for a subject in chronological order. Graphiti facts and bi-temporal filtering appear only when the optional
  • mneme_prime — Builds a token-budgeted preflight context bundle from recent sessions and topic-relevant matches. A caller session identifier enables per-session
  • mneme_propose — Queues a redacted memory-edit proposal for the policy drain. The server does not apply the edit directly; durable categories always require human
  • mneme_checkpoint_list — Lists recent Context Continuity Engine checkpoints from the active scope, newest first. Missing checkpoint state returns an empty list
  • mneme_working_set_load — Loads salience-ranked working-set items from a Context Continuity Engine checkpoint. Unknown and out-of-scope anchors return the same neutral

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Mneme.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Mneme's toolset — mneme_search, mneme_recall, mneme_write and 6 more — is a fair guide to whether it matches your workflow. It is maintained by OnourImpram; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Mneme's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
mneme_searchFTS5 BM25 retrieval over the vault with Turkish casefold normalization, plus date, memory-type, and scope filters. Returns ranked hits and EvidenceCards carrying content hashes, trust, confidence, and the backend that ac
mneme_recallRetrieves indexed documents by session identifier, date range, and scope. Returns paths, titles, modification times, memory types, and optionally the full markdown body.
mneme_writeAtomically appends or replaces a markdown section in a vault file. Enforces vault path containment and redacts private spans before storage.
mneme_summarizeGroups FTS5 matches for a topic by vault directory within optional date and scope filters. Graphiti enrichment appears only when that optional local graph integration is configured.
mneme_timelineReturns scope-restricted references for a subject in chronological order. Graphiti facts and bi-temporal filtering appear only when the optional local graph integration is available.
mneme_primeBuilds a token-budgeted preflight context bundle from recent sessions and topic-relevant matches. A caller session identifier enables per-session injection deduplication and full, keypoints, or reference formatting.
mneme_proposeQueues a redacted memory-edit proposal for the policy drain. The server does not apply the edit directly; durable categories always require human approval.
mneme_checkpoint_listLists recent Context Continuity Engine checkpoints from the active scope, newest first. Missing checkpoint state returns an empty list.
mneme_working_set_loadLoads salience-ranked working-set items from a Context Continuity Engine checkpoint. Unknown and out-of-scope anchors return the same neutral not-found result.

How to install the Mneme MCP server

{
  "mcpServers": {
    "mneme": {
      "command": "uvx",
      "args": ["mneme-cc-plugin"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Mneme to mneme search.
  • Use Mneme to mneme recall.
  • Use Mneme to mneme write.

Frequently asked questions

It connects Mneme to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (mneme_search, mneme_recall, mneme_write, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Mneme directly.