Skip to main content
Glama

EAG v3 — 带有 Prefab UI 的 MCP 演示

一个 FastMCP 服务器,包含三个工具,分别用于 (1) 互联网访问,(2) 本地文件 CRUD,以及 (3) 通过 Prefab 实现的生成式 UI。专为在 Claude Desktop 中运行而设计。

工具

工具

类型

用途

web_search(query)

互联网

DuckDuckGo 即时答案 API — 返回摘要 + 相关主题

notes_file(action, key, content)

本地 CRUD

单一工具,通过 ./notes.json 进行操作分发 (create / read / update / delete / list)

show_dashboard()

UI

将保存的笔记渲染为 Prefab 卡片网格(使用 @mcp.tool(app=True)

Related MCP server: MCP + CrewAI Agentic Integration

设置

需要 uv (brew install uv) 和 Claude Desktop。

cd /Users/nitingangwar/Documents/Code/eagv3/mcp
uv sync

连接到 Claude Desktop

编辑 ~/Library/Application Support/Claude/claude_desktop_config.json 并添加(或合并) mcpServers 块:

{
  "mcpServers": {
    "eag-mcp-demo": {
      "command": "/opt/homebrew/bin/uv",
      "args": [
        "run",
        "--directory",
        "/Users/nitingangwar/Documents/Code/eagv3/mcp",
        "python",
        "server.py"
      ]
    }
  }
}

重启 Claude Desktop。MCP 指示器应显示 eag-mcp-demo 以及三个工具。

纯 Python 回退(无 uv)

python3 -m venv .venv
.venv/bin/pip install -e .

然后在 Claude Desktop 配置中使用:

"command": "/Users/nitingangwar/Documents/Code/eagv3/mcp/.venv/bin/python",
"args": ["/Users/nitingangwar/Documents/Code/eagv3/mcp/server.py"]

演示提示词

在服务器连接后,将此内容粘贴到 Claude Desktop 中:

通过网页搜索查找 Tata Sons 的所有权详情,将 2-3 句摘要保存到我的笔记文件中,键名为 tata_sons,然后打开仪表板以便我查看。

预期行为:

  1. web_search("Tata Sons ownership") → DDG 摘要。

  2. notes_file("create", "tata_sons", "<summary>") → 写入 notes.json

  3. show_dashboard() → 内联渲染一个包含一张卡片的 Prefab 卡片网格。

换一家公司(例如“Reliance Industries”)重新运行,仪表板现在会显示两张卡片。

冒烟测试

# Server starts and blocks on stdin (correct):
uv run python server.py

# Or interactive inspector:
npx @modelcontextprotocol/inspector uv run python server.py

在检查器中:列出工具,调用 web_search("Tata Sons"),然后调用 notes_file("create", "x", "y") 并确认 notes.json 在磁盘上已更新。

回退方案

  • Prefab 渲染器未启动(Claude Desktop 返回 JSON 而不是 UI):将 show_dashboard 装饰器从 @mcp.tool(app=True) 更改为普通的 @mcp.tool,并使其返回一个由 notes.json 构建的 Markdown 表格。

  • DuckDuckGo 查询返回为空:DDG 仅对知名实体提供即时答案。演示时请使用著名的公司/人物/地点。

文件

server.py        # FastMCP server with the 3 tools
notes.json       # backing store for notes_file (starts as {})
pyproject.toml   # deps: fastmcp[apps], prefab-ui==0.19.1, httpx
Install Server
F
license - not found
A
quality
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    -
    quality
    D
    maintenance
    A FastMCP-based server that supports SSE real-time event streaming and tool calling, with features for text-to-JSON conversion and grouping text by JSON templates.
    MIT
  • A
    license
    A
    quality
    A
    maintenance
    A storage and retrieval MCP server for AI agents using FastMCP, enabling persistent knowledge base with semantic search and automatic linking.
    3
    292
    MIT
  • A
    license
    -
    quality
    B
    maintenance
    MCP server providing persistent memory, semantic search, versioned storage, webhook fanout, and unified LLM routing for AI agents via FastAPI runtime with multiple backend options.
    29
    Apache 2.0

View all related MCP servers

Related MCP Connectors

  • Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SkinnyMonk/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server