MCP FastAPI Chart Server
Generates matplotlib charts via a FastAPI service, supporting line, bar, scatter, and pie charts with customizable labels and data.
README
MCP FastAPI Chart Server
An MCP (Model Context Protocol) server that interacts with a FastAPI service to generate matplotlib charts.
Overview
This MCP server provides tools to:
- Generate charts using your FastAPI chart generation service
- Check the status of your FastAPI server
- Return chart images directly to the client
Prerequisites
- Python 3.8+
- Your FastAPI server running on
localhost:8000with the/plotendpoint
Installation
- Install the package:
pip install -e .
Configuration
For Claude Desktop
Add the following to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"fastapi-chart": {
"command": "python",
"args": ["-m", "mcp_fastapi_chart.server"]
}
}
}
For Other MCP Clients
Configure your MCP client to run:
python -m mcp_fastapi_chart.server
Available Tools
1. generate_chart
Generate a chart using the FastAPI chart generation service.
Parameters:
chart_type(string): Type of chart to generate - "line", "bar", "scatter", or "pie"title(string): Main title of the chartsubtitle(string): Subtitle of the chartx_label(string): Label for the X-axisy_label(string): Label for the Y-axisdata(object): Chart data with labels and valueslabels(array of strings): Labels for data pointsvalues(array of numbers): Values for data points
Example Usage:
{
"chart_type": "line",
"title": "Asylum Applications Trend",
"subtitle": "Monthly applications received (2023-2024)",
"x_label": "Month",
"y_label": "Applications Received",
"data": {
"labels": ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"],
"values": [15400, 16800, 14200, 18900, 17600, 19500, 20300, 18700, 17400, 16200, 15800, 14900]
}
}
2. check_fastapi_status
Check if the FastAPI server is running and accessible.
Parameters: None
FastAPI Server Requirements
Your FastAPI server should have an endpoint at /plot that accepts POST requests with the following JSON structure:
{
"chart_type": "string",
"title": "string",
"subtitle": "string",
"data": {
"labels": ["string"],
"values": [number]
},
"x_label": "string",
"y_label": "string"
}
And should return a PNG image as the response.
Development
To run the server directly for testing:
python -m mcp_fastapi_chart.server
Cloud Deployment
When you move your FastAPI server to the cloud, update the fastapi_base_url in mcp_fastapi_chart/server.py:
self.fastapi_base_url = "https://your-cloud-domain.com"
Troubleshooting
- Connection Errors: Make sure your FastAPI server is running on
localhost:8000 - Chart Generation Errors: Verify your FastAPI
/plotendpoint is working correctly - MCP Connection Issues: Check your Claude Desktop configuration file syntax
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。