MemoFS MCP Server

dev.memofsPublished by memofs.devOfficial publisherv1.3.0-beta.3Updated Oct 24, 2026

Persistent memory and virtual filesystem MCP server for AI agents.

VerifiedStreamable HTTPWeb executableFiles & StorageKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

MemoFS gives AI coding agents a persistent project memory and virtual filesystem to read, search and update across sessions.

What you can do
  • Read, search and update project memory through memory verbs such as remember and recall
  • Bind memories to source files with anchors and see stale flags when those files change
  • Flag memories as unverified when they pass their kind-specific decay floors
  • Run AgentFS session tools, including completing a session with an outcome, ephemeral setting and reason
  • Access memory, graph and session data through exposed resources
When to use it
Useful when you want a coding agent to keep durable project context between sessions, or to tie notes to specific source files and notice when they go out of date. Also relevant if you want a read-only memory layer for untrusted clients.
Requirements
Runs as a remote endpoint or as a local process via npx or npm; Node.js 22 or newer is required. Local mode needs a project root path. Hybrid mode needs a MemoFS Cloud API key, supplied as the MEMOFS_API_KEY environment variable or a bearer Authorization header, plus a cloud URL.
Before you install
Hybrid mode sends project memory to MemoFS Cloud and requires an API key; keep that key out of shared configs. The server can write and update memory, so use the read-only flag with untrusted clients. Session completion can promote memories durably and clean up workspaces.

Installation

In SourceWeft

  1. Open MemoFS MCP Server in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Follow the launch instructions in the repository.

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:

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

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

bash
npm install -D @memofs/mcp-server

Requires Node.js >= 22.

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

bash
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

json
{  "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

Source: packages/mcp-server/README.md at commit 8ebe942

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.3.0-beta.3LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts