Mnemoverse Memory

@mnemoverse/mcp-memory-server

Hosted memory for AI agents that learns which facts matter. Feedback re-ranks recall — a Rescorla-Wagner update on the prediction error, not a similarity score — so what helped rises and what misled sinks, with a bounded recency tie-breaker for fresh memories. The engine also ships consolidation (HDBSCAN clustering, with Von Restorff protection so distinctive memories survive compression). One API key works across Claude, Cursor, VS Code, ChatGPT, and any MCP client.

Memory that persists across sessions, projects, and tools — and improves with use. Hosted, so there's no infrastructure to run, and not locked to a single cloud.

⭐ If Mnemoverse saves you from re-explaining context to your agents, star the repo. It helps other builders find it.

Quick Start

1. Get a free API key

Sign up at console.mnemoverse.com — takes 30 seconds, no credit card.

2. Connect to your AI tool

Claude Code — add via CLI:

claude mcp add mnemoverse -s user \
  -e MNEMOVERSE_API_KEY=mk_live_YOUR_KEY \
  -e MNEMOVERSE_API_URL=https://core.mnemoverse.com/api/v1 \
  -- npx -y @mnemoverse/mcp-memory-server@latest

Cursor — click to install, or add to .cursor/mcp.json:

{
  "mcpServers": {
    "mnemoverse": {
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server@latest"
      ],
      "env": {
        "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY",
        "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1"
      }
    }
  }
}

VS Code — add to .vscode/mcp.json (note: VS Code uses servers, not mcpServers):

{
  "servers": {
    "mnemoverse": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server@latest"
      ],
      "env": {
        "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY",
        "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1"
      }
    }
  }
}

Windsurf — add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "mnemoverse": {
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server@latest"
      ],
      "env": {
        "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY",
        "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1"
      }
    }
  }
}

More MCP clients — same server, different config file:

Zed — add to ~/.config/zed/settings.json (Zed uses context_servers, and "source": "custom" is required):

{
  "context_servers": {
    "mnemoverse": {
      "source": "custom",
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server@latest"
      ],
      "env": {
        "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY",
        "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1"
      }
    }
  }
}

JetBrains (AI Assistant) — Settings → Tools → AI Assistant → Model Context Protocol (MCP), then paste:

{
  "mcpServers": {
    "mnemoverse": {
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server@latest"
      ],
      "env": {
        "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY",
        "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1"
      }
    }
  }
}

Cline — MCP Servers → Configure (or edit cline_mcp_settings.json). Cline reads env values literally, so paste your real key — not a ${VAR} reference:

{
  "mcpServers": {
    "mnemoverse": {
      "command": "npx",
      "args": [
        "-y",
        "@mnemoverse/mcp-memory-server@latest"
      ],
      "env": {
        "MNEMOVERSE_API_KEY": "mk_live_YOUR_KEY",
        "MNEMOVERSE_API_URL": "https://core.mnemoverse.com/api/v1"
      }
    }
  }
}

Continue — add ~/.continue/mcpServers/mnemoverse.yaml (Continue uses YAML):

mcpServers:
  - name: mnemoverse
    command: npx
    args:
      - "-y"
      - "@mnemoverse/mcp-memory-server@latest"
    env:
      MNEMOVERSE_API_KEY: "mk_live_YOUR_KEY"
      MNEMOVERSE_API_URL: "https://core.mnemoverse.com/api/v1"

Why @latest? Bare npx @mnemoverse/mcp-memory-server is cached indefinitely by npm and stops re-checking the registry. The @latest suffix forces a metadata lookup on every Claude Code / Cursor / VS Code session start (~100-300ms), so you always pick up new releases.

⚠️ Restart your AI client after editing the config. MCP servers are only picked up on client startup.

3. Try it — 30 seconds to verify it works

Paste this in your AI chat:

"Remember that my favourite TypeScript framework is Hono, and please call memory_write to save it."

Your agent should call memory_write and confirm the memory was stored.

Then open a new chat / new session (this is the whole point — memory survives restarts), and ask:

"What's my favourite TypeScript framework?"

Your agent should call memory_read, find the entry, and answer "Hono". If it does — you're wired up. Write whatever you want next.

If it doesn't remember: check that the client was fully restarted and the config has your real mk_live_... key, not the placeholder.

Tools

Tool	What it does
memory_write	Store a memory — insight, preference, lesson learned
memory_read	Search memories by natural language query (optional recency ordering, time bounds, author exclusion)
memory_list_recent	List newest memories first — no query; since/until bounds (inclusive) + cursor paging
memory_feedback	Rate memories as helpful or not (improves future recall)
memory_stats	Check how many memories stored, which domains exist
memory_create_room	Create a shared memory room; its address works as a domain on write/read
memory_invite_to_room	Mint a one-time invite (code + link) for a room you own
memory_join_room	Join a shared room with an invite code (mnvr_...)
memory_list_rooms	List rooms you own or joined, with each room's address to use as domain
vault_list	List Vault secrets by alias and purpose — the secret value is never returned

Ideas: What to Remember

• User preferences: "I use dark mode", "I prefer Tailwind over CSS modules"
• Project context: "This project uses PostgreSQL + Prisma", "Deploy to Railway"
• Lessons learned: "Always run tests before push on this repo"
• Decisions made: "We chose REST over GraphQL because of caching simplicity"
• People & roles: "Alice is the designer, Bob owns the API"
• Past mistakes: "Don't deploy on Fridays — learned this the hard way"

Universal Memory

The same API key works across all tools. Write a memory in Claude Code — read it in Cursor. Learn something in VS Code — your GPT Custom Action knows it too.

                    ┌── Claude Code (this MCP server)
                    ├── Cursor (this MCP server)
   Mnemoverse API ──├── VS Code (this MCP server)
   (one memory)     ├── GPT (Custom Actions)
                    ├── Python SDK (pip install mnemoverse)
                    └── REST API (curl)

Configuration

Env Variable	Required	Default
MNEMOVERSE_API_KEY	For every tool call — the server starts and lists its tools without one	—
MNEMOVERSE_API_URL	No	https://core.mnemoverse.com/api/v1

Links

Setup and reference

• Documentation
• Cursor · VS Code · Claude Code · ChatGPT
• Python SDK
• API Reference
• Console (get API key)

Background reading

• Memory MCP servers compared — thirteen shipping options, with pricing and registry presence
• How to choose a memory MCP server — the five questions that narrow the field
• What AI agent memory is — the category explained
• Is this a vector database? — what makes a memory layer different
• Shared memory for multi-agent systems — how Rooms work and when to use them

Project

• GitHub
• Releases
• MCP Registry entry
• Contributing

Privacy Policy

This server sends to the Mnemoverse API (core.mnemoverse.com), authenticated with your API key, what a tool call carries — and nothing else it can see. It does not read your AI client's conversation history, your local files, or anything you don't pass to a memory_* / vault_* tool. Stored memories live under your account; Mnemoverse never sells them and never shares them on its own. The one sharing path is the one you create yourself: inviting someone to a shared room grants their assistant access to that room's memories, bounded by the invite's scope.

What each tool sends:

Tool	Data sent
memory_write	the content, concepts, and domain you pass
memory_read	the query, plus any filters: domain, since/until, exclude_author, top_k, order_by
memory_list_recent	the feed filters: domain, since/until, exclude_author, limit, cursor
memory_feedback	the atom_ids being rated and the outcome score
memory_create_room	the room name and description
memory_invite_to_room	the room_id, invite scope, and expiry
memory_join_room	the invite code
memory_stats / memory_list_rooms / vault_list	no request body — authenticated GETs

One thing goes out that you did not explicitly request: since 0.8.1, when a search or feed comes back empty, the server sends one or two authenticated read-only GET probes (/memory/rooms and/or /memory/stats) so the empty answer can say what it did not cover. The probes carry your API key and nothing else, change no stored state, and are disclosed in the CHANGELOG.

Privacy Policy	https://mnemoverse.com/privacy
Retention & deletion	correct a wrong or stale memory by writing a fresh one; deletion is an administrative operation on the REST API, not exposed through this MCP server
Contact	hello@mnemoverse.com

License

MIT © Mnemoverse