mcpField
M
MemoFS MCP Server

MemoFS MCP Server

Remote
memofs.devMemory & Knowledge6Updated today
RepositoryVisit website

About MemoFS MCP Server

MemoFS MCP Server gives AI coding agents a way to read, search, and update persistent project memory, along with AgentFS session data. It includes code-anchored memories, stale and unverified indicators, and controls for promoting session outcomes into durable memory.

Key features

  1. 01Read, search, and update project memory
  2. 02Anchor memories to source files
  3. 03Flag stale or unverified memories
  4. 04Manage AgentFS session data
  5. 05Control durable memory promotion
  6. 06Expose memory, graph, and session resources

Use cases

  1. 01Recall project context while coding
  2. 02Find memories linked to changed source files
  3. 03Review or update stored project knowledge
  4. 04Manage session outcomes and memory cleanup

MCP support

Exposes 10 tools and 9 resources for memory and AgentFS session access to MCP clients. It runs over stdio and supports local or hybrid runtime modes.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://memofs.dev/api/v1/projects/{projectId}/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://memofs.dev/api/v1/projects/{projectId}/mcpAuth required
Packages
npm@memofs/mcp-server1.3.0-beta.3

Tools

Details

From the project README

@memofs/mcp-server

npm version   Status: Beta   npm downloads   CI   Docs   MIT License

Model Context Protocol server for MemoFS agent integrations.

What is this?

The @memofs/mcp-server package allows AI coding agents (like Claude Desktop, Cursor, Zed, and OpenCode) to securely read, search, and update project memory using the Model Context Protocol (MCP). It wraps the core runtime and exposes 10 model-facing tools (4 memory verbs + 6 AgentFS session tools) and 9 resources for memory, graph, and session access.

Key capabilities:

  • Code anchoring — memofs.remember accepts an optional anchor parameter to bind memories to source files; memofs.recall surfaces stale flags when anchored files change.
  • Memory decay detection — recall results carry unverified flags when memories exceed their kind-specific decay floors.
  • Session outcomes — memofs_agent_session_complete accepts outcome, ephemeral, and reason parameters controlling a 5-row behavior matrix for durable memory promotion and workspace cleanup.

Installation

Most MCP clients invoke the server on demand via npx — no install required:

npx -y @memofs/mcp-server --help

If you want to install the server as a dev dependency instead:

npm install -D @memofs/mcp-server

Requires Node.js >= 22.

Or use directly via npx in your client's configuration:

npx -y @memofs/mcp-server --help

Quick Start

You can configure your MCP client (e.g., Claude Desktop, Cursor, or any MCP client) to start the server via stdio.

MCP clients config
{
  "mcpServers": {
    "memofs": {
      "command": "npx",
      "args": [
        "-y",
        "@memofs/mcp-server",
        "--runtime",
        "local",
        "--root",
        "/absolute/path/to/project"
      ]
    }
  }
}

Configuration and Usage

The server supports two runtime modes (local, hybrid), cloud sync via --cloud-url and --api-key, and a strict --read-only flag to block mutating tools when used with untrusted clients.

For comprehensive setup instructions across all major AI tools, the full list of exposed tools and resources, and runtime mode options, please refer to the Full Documentation.

Contributing

See our central Contributing Guide and development scripts for details on formatting, linting, and testing within the monorepo.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.