Skip to main content
Glama
deenesjakoruzh
augmentedivan

Fabric MCP Server

by augmentedivan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript

fabric-mcp-服务器

目录

  1. 介绍

  2. 什么是模型上下文协议（MCP）？

  3. 特征

  4. 工具

  5. 安装

  6. 用法

  7. 与 VS Code 一起使用的配置

  8. 与 Cline 一起使用的技巧

  9. 故障排除

  10. 贡献

  11. 执照

Related MCP server: wrapmcp

介绍

fabric-mcp-server是一个模型上下文协议 (MCP) 服务器，旨在将 Fabric 模式公开为与 Cline 集成的工具。此集成利用 Fabric 存储库中 AI 驱动的模式执行，增强了 Cline 的功能。

什么是模型上下文协议（MCP）？

模型上下文协议 (MCP) 是一种规范，旨在促进 AI 系统与外部工具或资源之间的通信。它标准化了 AI 模型与数据库、API 和文件系统等各种功能交互的方式。MCP 服务器（例如fabric-mcp-server ）实现了此协议，使 AI 模型能够访问工具和资源，从而扩展其功能范围。

特征

  • 将织物图案作为工具公开：服务器将所有织物图案作为 Cline 内的单独工具提供。

  • 模式执行：用户可以直接在 Cline 任务中选择和执行织物模式。

  • 增强功能：集成 AI 驱动的模式执行以增强 Cline 的功能。

工具

fabric-mcp-server提供了多种 Fabric 模式的工具。例如：

  • analyze_claims

  • summarize

  • extract_wisdom

  • create_mermaid_visualization

  • 还有更多...

要查看可用模式的完整列表，您可以列出fabric/patterns目录中的目录。

安装

  1. 克隆存储库：将fabric-mcp-server存储库克隆到本地系统。

  2. 安装依赖项：导航到fabric-mcp-server目录并运行npm install 。

  3. 构建项目：运行npm run build来编译 TypeScript 代码。

用法

要将fabric-mcp-server与 Cline 一起使用：

  1. 确保服务器已安装并正在运行。

  2. 在您的 Cline 设置文件中配置 MCP 服务器。

  3. 在 Cline 中创建一个新任务并选择要使用的织物图案。

与 VS Code 一起使用的配置

  1. 克隆存储库：将fabric-mcp-server存储库克隆到本地系统。

  2. 安装依赖项：导航到fabric-mcp-server目录并运行npm install 。

  3. 构建项目：运行npm run build 。

  4. 配置 Cline 设置：将 MCP 服务器配置添加到您的 Cline 设置文件中。文件路径因操作系统而异：

    • Windows ： C:\Users\<username>\AppData\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json

    • macOS ： ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

    • Linux ： ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

    使用以下配置：

"fabric-mcp-server": {
  "command": "node",
  "args": [
    "<path-to-fabric-mcp-server>/build/index.js"
  ],
  "env": {},
  "disabled": false,
  "autoApprove": [],
  "transportType": "stdio",
  "timeout": 60
}

将<path-to-fabric-mcp-server>替换为你系统上fabric-mcp-server目录的实际路径。例如：

  • Windows ： "C:\\path\\to\\fabric-mcp-server\\build\\index.js"

  • macOS/Linux ： "/path/to/fabric-mcp-server/build/index.js"

  1. 重新启动 VSCode ：重新启动 VSCode 或重新加载 Cline 扩展以应用更改。

与 Cline 一起使用的技巧

为了最大限度地发挥fabric-mcp-server与 Cline 的优势，请在提示末尾添加use fabric-mcp-server或考虑将以下规则添加到.clinerules文件：

# 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.

该规则简化了 Cline 中新任务的工具选择过程。

故障排除

  • 确保fabric-mcp-server在您的 Cline 设置中正确配置。

  • 验证服务器是否正在运行并且可以访问。

  • 检查控制台输出是否有任何错误消息。

贡献

欢迎为fabric-mcp-server做出贡献。请参阅CONTRIBUTING.md文件，了解如何贡献。

执照

fabric-mcp-server在MIT 许可证下发布。

Available Tools

1 tool
recommend_toolC

Recommends the best Fabric pattern tool for a given task

ParametersJSON Schema
NameRequiredDescriptionDefault
inputYesThe user's task description

TDQS

C2.9/5.0
Behavior2/5

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.

Conciseness5/5

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.

Completeness2/5

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.

Parameters3/5

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.

Purpose4/5

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.

Usage Guidelines2/5

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. 1 tool update
    • First observedrecommend_tool
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

B3/5.0

Scored across 1 tool

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count2/5

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.

Completeness1/5

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

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-cli-catalog

    abcpro1
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that publishes CLI tools on your machine for discoverability by LLMs
    7 npm
    1
    MIT

  • wrapmcp

    SubZtep
    A
    license
    Not graded
    quality
    C
    maintenance
    Universal MCP server that wraps any CLI tool, enabling AI assistants to run commands via natural language.
    1
    MIT

  • mcdev-mcp

    use-ai-for-mc
    A
    license
    A
    quality
    B
    maintenance
    An 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.
    31
    30 npm
    15
    MIT

  • Discord MCP

    EncryptMan
    F
    license
    C
    quality
    C
    maintenance
    An MCP server that exposes Discord bot actions as tools for LLM clients.
    29
    1
    -