
Fabric Mcp
io.github.mpzarde由 GitHub 帳號 mpzarde 發布v1.0.0更新於 Oct 24, 2026
MCP server for Fabric AI patterns
發布方自己的服務:Fabric
概覽
讓助理對文字、檔案、網址與 YouTube 字幕執行 Fabric AI 模式,用於摘要、分析與學習。
- 可以做什麼
- 包裝 Fabric CLI,讓助理可以列出可用模式、依名稱執行任何模式,並使用預先設定的工具,例如 extract_wisdom、summarize、analyze_claims、create_quiz、to_flashcards、explain_code、summarize_git_diff、analyze_logs 與 analyze_incident。組合工具可一步完成抓取內容並套用模式:analyze_youtube_video、analyze_file 與 analyze_url。health_check 工具用來檢查 Fabric 與 yt-dlp 是否已安裝並完成設定。
- 適用情境
- 適合想在 Claude Desktop 或 Warp 中直接使用 Fabric 模式庫的情境,例如摘要文章、從影片擷取重點、產生閃卡或測驗、審閱 git diff,以及分析日誌與安全事件。如果你已經在使用 Fabric,並希望不必離開助理就能呼叫其模式,這個伺服器很合適。
- 執行需求
- 以 Node.js 本機程序透過 stdio 執行,僅支援桌面端。需要安裝 Fabric CLI 並在 PATH 中可用;YouTube 字幕功能還需要 yt-dlp。選用環境變數 FABRIC_PATH 與 YTDLP_PATH 可指定自訂 CLI 路徑。Fabric 本身需要設定 AI 供應商與 API 金鑰。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Fabric Mcp,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Fabric MCP Server
Model Context Protocol (MCP) server for Fabric - Daniel Miessler's AI-powered content processing framework.
This MCP server allows Claude (via Claude Desktop or Warp CLI) to use Fabric's extensive collection of AI patterns for content analysis, summarization, learning, coding, security analysis, and more.
Quick Start
-
Install Fabric (if not already installed):
See the official Fabric installation guide for detailed instructions.
-
Install yt-dlp (optional, for YouTube transcripts):
-
Download and Install:
- Download
fabric-mcp.mcpbfrom Releases - Double-click the file
- Click "Install" in Claude Desktop
- Restart Claude Desktop
- Download
-
Try it: Ask Claude: "List all fabric patterns"
Features
- 🚀 Direct CLI Integration: Uses Fabric CLI directly (no REST API server needed)
- 🔧 19 Pre-configured Tools: Direct access to commonly-used Fabric patterns plus combined analysis tools
- 🎯 Generic Pattern Runner: Run any Fabric pattern with
run_fabric_pattern - 📺 YouTube Support: Fetch video transcripts directly (requires yt-dlp)
- 🔍 Pattern Discovery: List all available patterns dynamically
- 📁 File & URL Analysis: Process files and web content with Fabric patterns
- 🏥 Health Check: Verify dependencies and configuration
Prerequisites
1. Install Fabric
If you don't have Fabric installed, follow the official Fabric installation guide.
2. Install yt-dlp (Optional)
Required only if you want to fetch YouTube transcripts:
3. Verify Installation
Installation
Option 1: Download and Install (Recommended) 🎉
The easiest way to install:
- Download the latest
fabric-mcp.mcpbfrom Releases - Double-click the downloaded file
- Claude Desktop will open and prompt you to install
- Click Install
- Restart Claude Desktop
- Done!
The .mcpb file is a self-contained bundle that includes everything needed.
Option 2: Build from Source
If you want to build from source:
Then either:
- Build the
.mcpbbundle:./build-mcpb.sh(createsfabric-mcp.mcpbyou can install) - Configure manually: See Configuration section below for manual setup
Configuration
For Claude Desktop
Note: If you installed using the
.mcpbbundle (Option 1), Claude Desktop configures this automatically. This section is only needed for manual builds.
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
Replace /absolute/path/to/fabric-mcp/ with your actual project path.
Optional environment variables (if needed):
For Warp CLI
Note: Manual configuration is required for Warp. Build from source or extract the
.mcpbbundle first.
Add to your Warp MCP configuration file:
macOS/Linux: ~/.warp/mcp_config.json
Replace /absolute/path/to/fabric-mcp/ with your actual project path.
Optional environment variables (if needed):
Restart Claude/Warp
After configuration:
- Claude Desktop: Restart the application
- Warp: Restart the terminal or run
warp mcp reload
Available Tools
Core Tools
health_check- Check if Fabric, yt-dlp, and other dependencies are installed and configuredlist_fabric_patterns- List all available Fabric patternsrun_fabric_pattern- Run any Fabric pattern with custom inputget_youtube_transcript- Fetch transcript from YouTube video
Combined Analysis Tools
These tools streamline common workflows by fetching content and applying patterns in one step. Benefits:
- ✅ No truncation: Complete content is passed directly to Fabric
- ✅ More efficient: Single tool call instead of multiple
- ✅ Better results: Fabric processes the full content without context window limits
analyze_youtube_video- Fetch YouTube transcript and apply a pattern in one stepanalyze_file- Read a file and apply a pattern in one stepanalyze_url- Fetch URL content and apply a pattern in one step
Pre-configured Pattern Tools
These patterns are exposed as dedicated tools with the fabric_ prefix:
Content Analysis
fabric_extract_wisdom- Extract key insights and quotes from contentfabric_summarize- Create concise summariesfabric_analyze_claims- Analyze and fact-check claimsfabric_analyze_paper- Analyze academic papers
Learning
fabric_create_quiz- Generate quiz questionsfabric_to_flashcards- Convert content to flashcards
Development
fabric_summarize_git_diff- Summarize git diffs for reviewsfabric_create_coding_project- Generate project structure from ideasfabric_explain_code- Explain code in simple terms
Security & Operations
fabric_analyze_logs- Analyze log filesfabric_analyze_incident- Analyze security incidents
Writing
fabric_improve_writing- Improve writing quality
Usage Examples
With Claude Desktop
Extract wisdom from a YouTube video:
Summarize an article:
Create flashcards from lecture notes:
Analyze a git diff:
Combined Analysis Tools
For efficiency, use the combined tools that fetch and analyze in one step:
Chaining Patterns
Claude can chain multiple patterns together:
Use Cases
Based on Daniel Miessler's Fabric patterns:
Content Processing
- YouTube video → extract wisdom / summarize
- Article / blog post → summarize, analyze claims
- Podcast transcript → extract wisdom, pull quotes
Writing & Development
- Idea → essay (via
create_coding_projector similar patterns) - Code diff → PR description (via
summarize_git_diff) - Meeting notes → user stories (via
run_fabric_patternwithagility_story)
Learning
- Any content → flashcards (via
to_flashcards) - Dense docs → glossary with analogies
- Video/article → quiz (via
create_quiz)
Security Analysis
- Malware samples → analysis (via
analyze_malware) - Log files → threat interpretation (via
analyze_logs) - Security scans → rules (via
run_fabric_pattern)
Troubleshooting
Check server health
Ask Claude: "Run a health check" - this will verify:
- Fabric installation and version
- Fabric configuration (API keys, patterns)
- yt-dlp installation (for YouTube support)
- Provide installation instructions if anything is missing
Common Issues
Fabric not found
Error: Failed to spawn fabric: ENOENT
Solutions:
- Install Fabric following the official installation guide
- Verify installation:
which fabricandfabric --version - If using a custom Fabric location, set
FABRIC_PATHin your MCP config
Pattern not found
Error: Pattern not found: pattern_name
Solutions:
- Ask Claude to list all patterns: "List all fabric patterns"
- Update patterns:
fabric --updatepatterns - Check spelling - use underscores (e.g.,
extract_wisdomnotextractWisdom)
YouTube transcripts not working
Error: Failed to fetch YouTube transcript
Solutions:
- Install yt-dlp:
brew install yt-dlp(macOS) orpip install yt-dlp - Verify:
yt-dlp --version - If using custom location, set
YTDLP_PATHin your MCP config
MCP server not appearing in Claude
Solutions:
- Verify config file location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
- macOS:
- Check JSON syntax with a validator
- Ensure path to
dist/index.jsis absolute - Restart Claude Desktop completely
- Check logs:
~/Library/Logs/Claude/mcp-server-fabric.log
Pattern execution timeout
Error: Fabric command timed out
Solutions:
- Large patterns may take time (default: 5 minutes)
- Check your Fabric API keys and quota
- Try with a smaller input first
Development
Build
Watch mode
Testing locally
Architecture
The MCP server:
- Exposes Fabric patterns as MCP tools
- Calls Fabric CLI directly with pattern names and input
- Returns results back to Claude/Warp
- No REST API server needed - uses CLI interface
Resources
- Fabric: https://github.com/danielmiessler/Fabric
- yt-dlp: https://github.com/yt-dlp/yt-dlp
- MCP Documentation: https://modelcontextprotocol.io
- MCP SDK: https://github.com/modelcontextprotocol/typescript-sdk
License
MIT
Contributing
Contributions welcome! Please open an issue or PR.
Credits
- Fabric by Daniel Miessler
- MCP by Anthropic
來源:README.md,提交 dc3238e
工具
0版本歷史
1- v1.0.0最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
其他 Fabric 整合
Fabric
so.fabric官方發布者
Fabric 的託管 MCP 服務,由 fabric.so 發布;需要憑證;Streamable HTTP。

Knowledge Fabric
由 GitHub 帳號 invarcore 發布
本機 MCP 伺服器,讓助理對存放在 PostgreSQL + pgvector 中的文件進行混合 RAG 檢索,並回傳附引用的證據包。

MCP Fabric (Minecraft)
由 GitHub 帳號 denfry 發布
通過mcpfabric模組(Fabric和NeoForge)檢視並遊玩Minecraft: Java Edition。AI 翻譯

Unifi Fabric Mcp Server
由 GitHub 帳號 swkstudios 發布
MCP server for UniFi Fabric: Network, Protect, Site Manager, InnerSpace, Carrier Fabric, Mobility.

Neblex Integration Fabric
由 GitHub 帳號 neblexhq 發布
Neblex Integration Fabric 遠端伺服器,讓助理在雲端或地端建置、測試並發佈 iPaaS 流程、應用程式、表單與 AI 代理。