Skip to content
Back to search

fabric-mcp

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

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/ksylvan/fabric-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/ksylvan/fabric-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/ksylvan--fabric-mcp/badge.svg)](/listings/ksylvan--fabric-mcp)

HTML

<a href="/listings/ksylvan--fabric-mcp"><img src="/api/listings/ksylvan--fabric-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

- Python >= 3.10 - [uv](https://github.com/astral-sh/uv) (Python package and environment manager) for developers

Installation From Source (for developers)

1. **Clone the repository:**

   git clone https://github.com/ksylvan/fabric-mcp.git
   cd fabric-mcp

2. **Install dependencies using uv sync:**

   uv sync --dev

This command ensures your virtual environment matches the dependencies in `pyproject.toml` and `uv.lock`, creating the environment on the first run if necessary.

3. **Activate the virtual environment (uv will create it if needed):**

- On macOS/Linux:

```bash source .venv/bin/activate ```

- On Windows:

```bash .venv\Scripts\activate ```

Now you have the development environment set up!

Installation From PyPI (for users)

If you just want to use the `fabric-mcp` server without developing it, you can install it directly from PyPI:

# Using pip
pip install fabric-mcp

# Or using uv
uv pip install fabric-mcp

This will install the package and its dependencies. You can then run the server using the `fabric-mcp` command.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 196 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Fabric MCP Server
  2. [![License: MIT][mit_license]][mit_license_link]
  3. [![image](https://img.shields.io/pypi/v/fabric-mcp.svg)](https://pypi.python.org/pypi/fabric-mcp)
  4. [![Ask DeepWiki](https://img.shields.io/badge/Ask-DeepWiki-blue)](https://deepwiki.com/ksylvan/fabric-mcp)
  5. [![Verified on MseeP](https://img.shields.io/badge/MseeP-verified-green)](https://mseep.ai/app/ksylvan-fabric-mcp)
  6. | main | | | develop | |
  7. |:---:|:---:|:---:|:---:|:---:|
  8. | [![Main Tests][main_tests]][main_tests_link] | [![Main Publish][main_publish]][main_publish_link] | | [![Develop Tests][develop_tests]][develop_tests_link] | [![Develop Publish][develop_publish]][develop_publish_link] |
  9. <div align="center">
  10. <img src="https://github.com/ksylvan/fabric-mcp/blob/main/docs/logo.png?raw=true" alt="fabric-mcp logo" width="200" height="200">
  11. <a href="https://mseep.ai/app/ksylvan-fabric-mcp"><img src="https://mseep.net/pr/ksylvan-fabric-mcp-badge.png" alt="MseeP.ai Security Assessment Badge" height="200"></a>
  12. </div>
  13. Connect the power of the Fabric AI framework to any Model Context Protocol (MCP) compatible application.
  14. This project implements a standalone server that bridges the gap between [Daniel Miessler's Fabric framework][fabricGithubLink] and the [Model Context Protocol (MCP)][MCP]. It allows you to use Fabric's patterns, models, and configurations directly within MCP-enabled environments like IDE extensions or chat interfaces.
  15. Imagine seamlessly using Fabric's specialized prompts for code explanation, refactoring, or creative writing right inside your favorite tools!
  16. ## Table of Contents
  17. - [Fabric MCP Server](#fabric-mcp-server)
  18. - [Table of Contents](#table-of-contents)
  19. - [What is this?](#what-is-this)
  20. - [Key Goals \& Features (Based on Design)](#key-goals--features-based-on-design)
  21. - [How it Works](#how-it-works)
  22. - [Project Status](#project-status)
  23. - [Getting Started](#getting-started)
  24. - [Prerequisites](#prerequisites)
  25. - [Installation From Source (for developers)](#installation-from-source-for-developers)
  26. - [Installation From PyPI (for users)](#installation-from-pypi-for-users)
  27. - [Configuration (Environment Variables)](#configuration-environment-variables)
  28. - [Transport Options](#transport-options)
  29. - [Contributing](#contributing)
  30. - [License](#license)
  31. ## What is this?
  32. - **Fabric:** An open-source framework for augmenting human capabilities using AI, focusing on prompt engineering and modular AI workflows.
  33. - **MCP:** An open standard protocol enabling AI applications (like IDEs) to securely interact with external tools and data sources (like this server).
  34. - **Fabric MCP Server:** This project acts as an MCP server, translating MCP requests into calls to a running Fabric instance's REST API (`fabric --serve`).
  35. ## Key Goals & Features (Based on Design)
  36. - **Seamless Integration:** Use Fabric patterns and capabilities directly within MCP clients without switching context.
  37. - **Enhanced Workflows:** Empower LLMs within IDEs or other tools to leverage Fabric's specialized prompts and user configurations.
  38. - **Standardization:** Adhere to the open MCP standard for AI tool integration.
  39. - **Leverage Fabric Core:** Build upon the existing Fabric CLI and REST API without modifying the core Fabric codebase.
  40. - **Expose Fabric Functionality:** Provide MCP tools to list patterns, get pattern details, run patterns, list models/strategies, and retrieve configuration.
  41. - **Expose Pattern Prompts:** Fabric patterns are also exposed as MCP prompts so users can discover and invoke reusable pattern templates directly through prompt-aware clients.
  42. ## How it Works
  43. 1. An **MCP Host** (e.g., an IDE extension) connects to this **Fabric MCP Server**.
  44. 2. The Host discovers available tools (like `fabric_run_pattern`) via MCP's `list_tools()` mechanism and available Fabric pattern templates via MCP's `prompts/list` mechanism.
  45. 3. When the user invokes a tool or prompt (e.g., asking the IDE's AI assistant to refactor code using a Fabric pattern), the Host sends an MCP request to this server.
  46. 4. The **Fabric MCP Server** translates the MCP request into a corresponding REST API call to a running `fabric --serve` instance.
  47. 5. The `fabric --serve` instance executes the pattern.
  48. 6. The **Fabric MCP Server** receives the response (potentially streaming) from Fabric and translates it back into an MCP response for the Host.
  49. ## Project Status
  50. This project is feature-complete.
  51. The project was completed by using the [BMAD-METHOD (Breakthrough Method of Agile Ai-Driven Development)][bmad-method].
  52. The core architecture and proposed tools are outlined in the [High-Level Architecture Document][architecture_doc].
  53. You can also use [![Ask DeepWiki](https://img.shields.io/badge/Ask-DeepWiki-blue)](https://deepwiki.com/ksylvan/fabric-mcp) to explore the source code.
  54. ## Getting Started
  55. These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
  56. ### Prerequisites
  57. - Python >= 3.10
  58. - [uv](https://github.com/astral-sh/uv) (Python package and environment manager) for developers
  59. ### Installation From Source (for developers)
  60. 1. **Clone the repository:**
  61. ```bash
  62. git clone https://github.com/ksylvan/fabric-mcp.git
  63. cd fabric-mcp
  64. ```
  65. 2. **Install dependencies using uv sync:**
  66. ```bash
  67. uv sync --dev
  68. ```
  69. This command ensures your virtual environment matches the dependencies in `pyproject.toml` and `uv.lock`, creating the environment on the first run if necessary.
  70. 3. **Activate the virtual environment (uv will create it if needed):**
  71. - On macOS/Linux:
  72. ```bash
  73. source .venv/bin/activate
  74. ```
  75. - On Windows:
  76. ```bash
  77. .venv\Scripts\activate
  78. ```
  79. Now you have the development environment set up!
  80. ### Installation From PyPI (for users)
  81. If you just want to use the `fabric-mcp` server without developing it, you can install it directly from PyPI:
  82. ```bash
  83. # Using pip
  84. pip install fabric-mcp
  85. # Or using uv
  86. uv pip install fabric-mcp
  87. ```
  88. This will install the package and its dependencies. You can then run the server using the `fabric-mcp` command.
  89. ## Configuration (Environment Variables)
  90. The `fabric-mcp` server can be configured using the following environment variables:
  91. - **`FABRIC_BASE_URL`**: The base URL of the running Fabric REST API server (`fabric --serve`).
  92. - *Default*: `http://127.0.0.1:8080`
  93. - **`FABRIC_API_KEY`**: The API key required to authenticate with the Fabric REST API server, if it's configured to require one.
  94. - *Default*: None (Authentication is not attempted if not set).
  95. - **`FABRIC_MCP_LOG_LEVEL`**: Sets the logging verbosity for the `fabric-mcp` server itself.
  96. - *Options*: `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` (case-insensitive).
  97. - *Default*: `INFO`
  98. You can set these variables in your shell environment (or put them into a `.env` file in the working directory) before running `fabric-mcp`:
  99. ```bash
  100. export FABRIC_BASE_URL="http://your-fabric-host:port"
  101. # This must match the key used by fabric --serve
  102. export FABRIC_API_KEY="your_secret_api_key"
  103. export FABRIC_MCP_LOG_LEVEL="DEBUG"
  104. # Standard I/O transport (default)
  105. fabric-mcp --stdio
  106. # HTTP Streamable transport for HTTP-based MCP clients
  107. fabric-mcp --http-streamable
  108. # Custom host/port for HTTP transport
  109. fabric-mcp --http-streamable --host 0.0.0.0 --port 3000 --mcp-path /message
  110. ```
  111. ### Transport Options
  112. The `fabric-mcp` server supports multiple transport methods:
  113. - **`--stdio`**: Standard I/O transport for direct MCP client integration (default)
  114. - **`--http-streamable`**: HTTP-based transport that runs a full HTTP server for MCP communication
  115. - `--host`: Server bind address (default: 127.0.0.1)
  116. - `--port`: Server port (default: 8000)
  117. - `--mcp-path`: MCP endpoint path (default: /message)
  118. For more details on transport configuration, see the [Infrastructure and Deployment Overview](./docs/architecture/infrastructure-and-deployment-overview.md#transport-configuration).
  119. ## Contributing
  120. Read the [contribution document here](./docs/contributing.md) and please follow the guidelines for this repository.
  121. Also refer to the [cheat-sheet for contributors](./docs/contributing-cheatsheet.md) which contains a micro-summary of the
  122. development workflow.
  123. ## License
  124. Copyright (c) 2025, [Kayvan Sylvan](kayvan@sylvan.com) Licensed under the [MIT License](./LICENSE).
  125. [fabricGithubLink]: https://github.com/danielmiessler/fabric
  126. [MCP]: https://modelcontextprotocol.io/
  127. [architecture_doc]: ./docs/architecture/index.md
  128. [develop_publish_link]: https://github.com/ksylvan/fabric-mcp/actions/workflows/publish.yml?branch=develop
  129. [develop_publish]: https://github.com/ksylvan/fabric-mcp/actions/workflows/publish.yml/badge.svg?branch=develop
  130. [develop_tests_link]: https://github.com/ksylvan/fabric-mcp/actions/workflows/tests.yml?branch=develop
  131. [develop_tests]: https://github.com/ksylvan/fabric-mcp/actions/workflows/tests.yml/badge.svg?branch=develop
  132. [mit_license_link]: https://opensource.org/licenses/MIT
  133. [mit_license]: https://img.shields.io/badge/License-MIT-yellow.svg
  134. [main_publish_link]: https://github.com/ksylvan/fabric-mcp/actions/workflows/publish.yml
  135. [main_publish]: https://github.com/ksylvan/fabric-mcp/actions/workflows/publish.yml/badge.svg
  136. [main_tests_link]: https://github.com/ksylvan/fabric-mcp/actions/workflows/tests.yml
  137. [main_tests]: https://github.com/ksylvan/fabric-mcp/actions/workflows/tests.yml/badge.svg
  138. [bmad-method]: https://github.com/bmadcode/BMAD-METHOD

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.