What is MCP?

The Model Context Protocol (MCP) is a standard for AI agent communication. Memento provides an MCP server with 16 tools that AI agents can use to manage persistent memory.

Available Tools

Tool	Description
mem_save	Save an observation
mem_search	Search observations (FTS5)
mem_get_observation	Get full observation by ID
mem_update	Update an existing observation
mem_delete	Delete/restore/purge observations
mem_context	Get recent context for recovery
mem_session_start	Start a new session
mem_session_end	End current session
mem_session_summary	Create end-of-session summary
mem_capture_passive	Parse text for learnings
mem_timeline	Chronological observation list
mem_status	System diagnostics
mem_merge	Merge related observations
mem_export	Export observations (JSON/XML/TXT)
mem_lock / mem_unlock	Lock/unlock observations
mem_pin / mem_unpin	Pin/unpin for system prompt injection

Editor Configuration

Memento works with any MCP-compatible editor or CLI. Choose yours below.

1. Claude Code

The most popular AI coding agent by Anthropic.

Project-level config: Create .mcp.json in your project root:

{
  "mcpServers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

Global config: Edit ~/.claude/claude_desktop_config.json to apply across all projects.

---

2. OpenCode

Open source terminal-based AI coding agent.

Add to your .opencode.json in the project root:

{
  "mcpServers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

---

3. Cursor

AI-first code editor.

Option A — UI: Go to Settings → MCP → Add new server and paste the config.

Option B — File: Create .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

---

4. Windsurf

AI code editor by Codeium (formerly Codeium).

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

You can also configure it via Windsurf Settings → Cascade → MCP Servers.

---

5. VS Code (GitHub Copilot)

VS Code with native MCP support for GitHub Copilot.

Create .vscode/mcp.json in your project root:

{
  "servers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

Note: VS Code uses the "servers" key — not "mcpServers".

You can also run MCP: Add Server from the Command Palette (Ctrl+Shift+P) for a guided setup.

---

6. Zed

High-performance, Rust-based code editor with built-in AI.

Add to your Zed settings file (~/.config/zed/settings.json):

{
  "context_servers": {
    "memento": {
      "command": "memento-mcp",
      "args": []
    }
  }
}

Note: Zed uses the "context_servers" key — not "mcpServers". Restart Zed after saving.

---

7. JetBrains AI

AI assistant for IntelliJ IDEA, WebStorm, PyCharm, and other JetBrains IDEs.

1. Open Settings → Tools → AI Assistant → MCP Servers
2. Click Add Server
3. Set the command to memento-mcp

No JSON config file needed — everything is configured through the IDE UI.

---

8. Aider

Terminal-based AI pair programmer.

Launch Aider with the --mcp-server flag:

aider --mcp-server memento-mcp

No config file needed. Aider will discover the Memento tools automatically.

---

9. Cline

Autonomous coding agent for VS Code.

Project-level config: Create .cline/mcp.json in your project root:

{
  "mcpServers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

You can also configure it from the Cline sidebar → MCP Servers → Edit Global MCP or Edit Project MCP.

---

10. Roo Code

AI coding agent extension for VS Code.

Project-level config: Create .roo/mcp.json in your project root:

{
  "mcpServers": {
    "memento": {
      "command": "memento-mcp"
    }
  }
}

You can also open the MCP settings from the Roo Code sidebar and click Edit Project MCP.

Usage Patterns

Session Workflow

The recommended workflow for AI agents:

1. mem_session_start(project: "my-app")
2. mem_context() — recover previous context
3. ... do work, save observations ...
4. mem_session_summary() — persist session summary
5. mem_session_end() — close session

Saving Observations

// Decision
mem_save({
  title: "Chose Zustand over Redux",
  type: "decision",
  content: "What: Using Zustand for state management\nWhy: Simpler API, less boilerplate",
  topic_key: "architecture/state-management",
  project: "my-app"
})

// Bug fix
mem_save({
  title: "Fixed N+1 in UserList",
  type: "bug",
  content: "What: Added batch loading for user profiles\nWhy: N+1 query causing 5s load time",
  topic_key: "bugfix/n1-userlist",
  project: "my-app"
})

Searching Memory

// Full-text search
mem_search({ query: "database choice" })

// Filter by type and project
mem_search({ query: "auth", type: "decision", project: "my-app" })

Tips

• Always start a session — observations are grouped by session for context recovery
• Use topic keys — stable keys like architecture/auth-model enable grouping and merging
• Save proactively — don't wait to be asked. Save decisions, bugs, and discoveries immediately
• Use mem_session_summary at session close — this persists what was done for next session