Fabric MCP Server
fabric-mcp-server
목차
Related MCP server: wrapmcp
소개
fabric-mcp-server 는 Cline과의 통합을 위한 도구로 Fabric 패턴을 노출하도록 설계된 모델 컨텍스트 프로토콜(MCP) 서버입니다. 이 통합은 Fabric 저장소의 AI 기반 패턴 실행을 활용하여 Cline의 기능을 향상시킵니다.
모델 컨텍스트 프로토콜(MCP)이란 무엇입니까?
모델 컨텍스트 프로토콜(MCP)은 AI 시스템과 외부 도구 또는 리소스 간의 통신을 용이하게 하는 사양입니다. AI 모델이 데이터베이스, API, 파일 시스템과 같은 다양한 기능과 상호 작용하는 방식을 표준화합니다. fabric-mcp-server 와 같은 MCP 서버는 이 프로토콜을 구현하여 AI 모델이 도구와 리소스에 접근할 수 있도록 하여 기능 범위를 확장합니다.
특징
패브릭 패턴을 도구로 공개 : 이 서버는 모든 패브릭 패턴을 Cline 내에서 개별 도구로 사용할 수 있도록 합니다.
패턴 실행 : 사용자는 Cline 작업 내에서 Fabric 패턴을 직접 선택하고 실행할 수 있습니다.
향상된 기능 : AI 기반 패턴 실행을 통합하여 Cline의 기능을 강화합니다.
도구
fabric-mcp-server 다양한 Fabric 패턴을 도구로 제공합니다. 몇 가지 예는 다음과 같습니다.
analyze_claimssummarizeextract_wisdomcreate_mermaid_visualization그리고 더 많은 것들이 있습니다...
사용 가능한 패턴의 전체 목록을 보려면 fabric/patterns 디렉토리에 디렉토리를 나열하세요.
설치
저장소 복제 :
fabric-mcp-server저장소를 로컬 시스템에 복제합니다.종속성 설치 :
fabric-mcp-server디렉토리로 이동하여npm install실행합니다.프로젝트 빌드 :
npm run build실행하여 TypeScript 코드를 컴파일합니다.
용법
Cline과 함께 fabric-mcp-server 사용하려면:
서버가 설치되고 실행 중인지 확인하세요.
Cline 설정 파일에서 MCP 서버를 구성합니다.
Cline에서 새로운 작업을 만들고 사용할 패브릭 패턴을 선택하세요.
VS Code 사용을 위한 구성
저장소 복제 :
fabric-mcp-server저장소를 로컬 시스템에 복제합니다.종속성 설치 :
fabric-mcp-server디렉토리로 이동하여npm install실행합니다.프로젝트 빌드 :
npm run build실행합니다.Cline 설정 구성 : MCP 서버 구성을 Cline 설정 파일에 추가합니다. 파일 경로는 운영 체제에 따라 다릅니다.
Windows :
C:\Users\<username>\AppData\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.jsonmacOS :
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json리눅스 :
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
다음 구성을 사용하세요.
지엑스피1
<path-to-fabric-mcp-server> 시스템의 fabric-mcp-server 디렉터리의 실제 경로로 바꾸세요. 예:
Windows :
"C:\\path\\to\\fabric-mcp-server\\build\\index.js"macOS/Linux :
"/path/to/fabric-mcp-server/build/index.js"
VSCode를 다시 시작합니다 . VSCode를 다시 시작하거나 Cline 확장 프로그램을 다시 로드하여 변경 사항을 적용합니다.
클라인과 함께 사용하기 위한 팁
Cline에서 fabric-mcp-server 의 이점을 극대화하려면 프롬프트 끝에 use fabric-mcp-server 추가하거나 .clinerules 파일에 다음 규칙을 추가하는 것을 고려하세요.
# Fabric MCP Server Rule
1. **List Fabric Patterns**: When a new task is created, list all pattern names from the Fabric repository.
2. **Prompt for Pattern Selection**: Ask the user to select one of the following options:
a) Enter a pattern name from the list to use the `fabric-mcp-server` tool with the specified pattern.
b) Choose not to use `fabric-mcp-server` for the task.이 규칙은 클라인의 새로운 작업을 위한 도구 선택 프로세스를 간소화합니다.
문제 해결
Cline 설정에서
fabric-mcp-server올바르게 구성되었는지 확인하세요.서버가 실행 중이고 접속 가능한지 확인하세요.
콘솔 출력에서 오류 메시지를 확인하세요.
기여하다
fabric-mcp-server 에 대한 기여를 환영합니다. 기여 방법에 대한 지침은 CONTRIBUTING.md 파일을 참조하세요.
특허
fabric-mcp-server MIT 라이선스 에 따라 배포됩니다.
Available Tools
1 toolrecommend_toolC
Recommends the best Fabric pattern tool for a given task
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | The user's task description |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'recommends' but does not clarify how recommendations are generated (e.g., based on criteria, algorithms, or data sources), whether it requires specific permissions, or what the output format entails. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and efficiently conveys the essential information, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (a recommendation function with no annotations or output schema), the description is incomplete. It lacks details on how recommendations are made, what criteria are used, the format of the output, or any behavioral traits. This makes it inadequate for an agent to fully understand and use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the parameter 'input' documented as 'The user's task description.' The description adds no additional meaning beyond this, such as examples or constraints. According to the rules, when schema coverage is high (>80%), the baseline score is 3, which applies here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Recommends the best Fabric pattern tool for a given task.' It specifies the verb ('recommends') and resource ('Fabric pattern tool'), making the function understandable. However, with no sibling tools provided, it cannot demonstrate differentiation from alternatives, preventing a score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or specific contexts. It merely restates the tool's function without indicating appropriate scenarios or exclusions, which is insufficient for effective agent decision-making.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
recommend_tool
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to confuse it with. The tool's purpose is clearly defined and distinct by default.
The single tool name 'recommend_tool' follows a consistent verb_noun pattern, and with only one tool, there is no inconsistency to evaluate. The naming is clear and predictable.
A single tool is too few for most server purposes, as it severely limits functionality and scope. This feels thin and incomplete for a server named 'Fabric MCP Server', which might imply broader capabilities.
The server is severely incomplete; with only a recommendation tool, there are obvious gaps in the surface. It lacks any tools to actually execute or manage Fabric patterns, making it impossible for agents to perform core tasks beyond getting advice.
Maintenance
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that publishes CLI tools on your machine for discoverability by LLMs7 npm1MIT
- AlicenseNot gradedqualityCmaintenanceUniversal MCP server that wraps any CLI tool, enabling AI assistants to run commands via natural language.1MIT
- AlicenseAqualityBmaintenanceAn MCP server that empowers AI coding agents to work effectively with Minecraft mod development, providing static analysis of decompiled source code and runtime interaction with a running Minecraft instance.3130 npm15MIT
- FlicenseCqualityCmaintenanceAn MCP server that exposes Discord bot actions as tools for LLM clients.291-