mcpField
F
Fabric

Fabric

Local
github.com/futurebrowserAI & Agents0Updated 4w ago
Repository

About Fabric

Fabric is an MCP server plugin for Cursor and Claude Code that lets agents work with a Fabric workspace in natural language. It combines search and management for saved content, memories, and tasks.

Key features

  1. 01Keyword and semantic search
  2. 02Create and manage notes and bookmarks
  3. 03Manage persistent workspace memories
  4. 04Create, edit, delete, and list tasks
  5. 05Organize content with folders, tags, and labels

Use cases

  1. 01Find saved links, files, notes, and tags
  2. 02Maintain workspace notes and bookmarks
  3. 03Track work with workspace tasks

MCP support

The Fabric MCP server exposes workspace search and management capabilities to connected agents, including tools for content, memories, and tasks.

#fabric#productivity#second-brain#ai-agent#data-connections#personal-server#notes#files#link#bookmarks#memory#memories

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "fabric-agent-plugins": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote"
      ]
    }
  }
}
Run commandnpx -y mcp-remote

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-remote

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Fabric agent plugin

This repository contains the configuration needed to integrate Fabric with Cursor IDE and Claude Code.

The plugin enables your agents to interact directly with your Fabric workspace, allowing you to search, save, and manage your links, notes, and memory, all through natural language.

Features

The Fabric MCP server provides the following capabilities:

  • Search: Find saved links, files, notes, and tags using keyword and semantic similarity search

  • Notes & Bookmarks: Create, edit, read, and delete notes and bookmarks; organize content into folders and move items between them

  • Memory: Create, search, edit, and manage persistent memories across your workspace

  • Tasks: Create, edit, delete, and list tasks to track your work

  • Organization: Rename, move, tag, and apply labels to keep your workspace structured

Quick links

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.