MCPgee
MCPgee
MCPgeeMCPgee

Fabric

v1.0.0•Communication•stable

Fabric MCP Server: Seamlessly integrate Fabric AI capabilities into MCP-enabled tools like IDEs and chat interfaces.

aimcpmcp-serveropen-source
Share:
86
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Fabric?

Fabric is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to fabric mcp server: seamlessly integrate fabric ai capabilities into mcp-enabled tools like ides and chat interfaces.

Fabric MCP Server: Seamlessly integrate Fabric AI capabilities into MCP-enabled tools like IDEs and chat interfaces.

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Fabric MCP Server: Seamlessly integrate Fabric AI capabiliti

Use Cases

Fabric AI integration
MCP tool and IDE integration
AI capability access
ksylvan

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx fabric

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Fabric

The Fabric MCP Server bridges the open-source Fabric AI framework into any MCP-compatible tool such as Claude Desktop, VS Code extensions, or chat interfaces. Fabric is a modular system of reusable AI patterns for tasks like summarizing content, explaining code, drafting reports, and extracting insights. By running this server, those patterns become first-class MCP tools that an AI agent can discover and invoke without leaving the IDE or chat session.

Prerequisites

  • Python 3.10 or later and pip or uv package manager
  • A running Fabric REST API server (fabric --serve) accessible on your network
  • Fabric installed and configured with at least one pattern: https://github.com/danielmiessler/fabric
  • An MCP client such as Claude Desktop, Claude Code, or any MCP-compatible IDE
1

Install Fabric and start its REST API server

Install the Fabric CLI tool and start it in server mode so the MCP server has an endpoint to connect to. By default it listens on port 8080.

pip install fabric
fabric --serve
2

Install fabric-mcp from PyPI

Install the MCP server package using pip or the faster uv tool.

pip install fabric-mcp
# or with uv:
uv pip install fabric-mcp
3

Configure environment variables

Set FABRIC_BASE_URL to point to your running Fabric server. If your server requires authentication, also set FABRIC_API_KEY.

export FABRIC_BASE_URL=http://127.0.0.1:8080
export FABRIC_API_KEY=your_optional_api_key
4

Add the server to your MCP client configuration

Register fabric-mcp in your Claude Desktop config. The server communicates over stdio by default.

{
  "mcpServers": {
    "fabric": {
      "command": "fabric-mcp",
      "args": [],
      "env": {
        "FABRIC_BASE_URL": "http://127.0.0.1:8080",
        "FABRIC_API_KEY": ""
      }
    }
  }
}
5

Restart your MCP client and test

Restart Claude Desktop or your IDE. The available Fabric patterns will appear as MCP tools and prompts. Ask the assistant to list available patterns to confirm connectivity.

6

Optional: run the server over HTTP for remote access

For shared or networked deployments, start fabric-mcp in HTTP streamable mode on a custom host and port.

fabric-mcp --http-streamable --host 0.0.0.0 --port 3000 --mcp-path /message

Fabric Examples

Client configuration

Claude Desktop JSON config for fabric-mcp using stdio transport with the Fabric API URL.

{
  "mcpServers": {
    "fabric": {
      "command": "fabric-mcp",
      "args": [],
      "env": {
        "FABRIC_BASE_URL": "http://127.0.0.1:8080",
        "FABRIC_API_KEY": "",
        "FABRIC_MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

Prompts to try

Example prompts leveraging Fabric patterns via the MCP server.

- "List all available Fabric patterns."
- "Use the summarize pattern to condense this article: [paste article text]"
- "Run the explain_code pattern on this Python function: [paste code]"
- "What models are available on my Fabric server?"
- "Execute the extract_wisdom pattern on this YouTube transcript: [paste transcript]"

Troubleshooting Fabric

Connection refused errors when the MCP server starts

Ensure the Fabric REST API is running with 'fabric --serve' and that FABRIC_BASE_URL matches the actual host and port. Check that no firewall is blocking port 8080.

No patterns appear as MCP tools

Verify that Fabric has patterns installed by running 'fabric --list' in a terminal. If no patterns are listed, download them with 'fabric --update' or follow the Fabric setup guide at https://github.com/danielmiessler/fabric.

Authentication errors when FABRIC_API_KEY is set

Confirm the API key matches what was configured when starting 'fabric --serve'. If your server does not require authentication, leave FABRIC_API_KEY empty rather than omitting the variable.

Frequently Asked Questions about Fabric

What is Fabric?

Fabric is a Model Context Protocol (MCP) server that fabric mcp server: seamlessly integrate fabric ai capabilities into mcp-enabled tools like ides and chat interfaces. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Fabric?

Follow the installation instructions on the Fabric GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Fabric?

Fabric works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Fabric free to use?

Yes, Fabric is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Fabric Alternatives — Similar Communication Servers

Looking for alternatives to Fabric? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.

Slack

★ 86.1k

Enables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl

LibreChat

★ 37.3k

Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA

Note Gen

★ 11.9k

A cross-platform Markdown AI note-taking software.

DeepChat

★ 5.8k

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

WhatsApp MCP

★ 5.7k

Connects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without

Apple

★ 3.1k

Enables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

CommunicationBrowse All Servers

Quick Config Preview

{ "mcpServers": { "fabric": { "command": "npx", "args": ["-y", "fabric"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Fabric?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides