Skip to main content

Python sandbox MCP server for matplotlib visualization

Project description

Python Plot MCP

一个专注于 Python 画图的 MCP (Model Context Protocol) 服务器,支持在云端执行 Python 代码并生成 matplotlib 图表。

功能特点

  • Python 沙箱执行:安全隔离的 Python 代码执行环境
  • Matplotlib 支持:内置 matplotlib 和中文字体
  • Base64 图像返回:生成的图表直接返回为 data URL
  • 完整 MCP 协议:符合 MCP 标准
  • 多种安装方式:支持 uvx、pip、npx

安装

方式一:uvx(推荐 - 魔搭平台)

uvx python-plot-mcp

方式二:pip

pip install python-plot-mcp
python-plot-mcp

方式三:npx(Node.js)

npx python-plot-sandbox-mcp

使用

魔搭平台配置

在魔搭 MCP 广场或支持 MCP 的客户端中配置:

{
  "mcpServers": {
    "python-plot": {
      "command": "uvx",
      "args": ["python-plot-mcp"]
    }
  }
}

本地开发配置

{
  "mcpServers": {
    "python-plot": {
      "command": "python",
      "args": ["-m", "python_plot_mcp"]
    }
  }
}

工具:run_python

执行 Python 代码并生成图表。

参数

  • code (string, 必需): Python 代码
  • timeout_s (integer, 可选): 超时时间(秒),默认 12
  • return_inline_image (boolean, 可选): 返回 base64 图片,默认 true

示例

import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 10, 100)
y = np.sin(x)

plt.figure(figsize=(10, 6))
plt.plot(x, y)
plt.title('正弦波')
plt.xlabel('x')
plt.ylabel('sin(x)')
plt.grid(True)
plt.show()

依赖

  • Python 3.9+
  • matplotlib
  • numpy
  • Pillow

许可证

MIT

作者

Your Name

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

python_plot_mcp-1.0.3.tar.gz (5.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

python_plot_mcp-1.0.3-py3-none-any.whl (6.5 kB view details)

Uploaded Python 3

File details

Details for the file python_plot_mcp-1.0.3.tar.gz.

File metadata

  • Download URL: python_plot_mcp-1.0.3.tar.gz
  • Upload date:
  • Size: 5.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.2

File hashes

Hashes for python_plot_mcp-1.0.3.tar.gz
Algorithm Hash digest
SHA256 54dea79dddf3321d7b9b02384263e3ad259d457287b2832d7507166e7c28bb67
MD5 12f55741ad5ec3d1aeefa6909af24866
BLAKE2b-256 1cfe8a01341b130f76642406cda95fe72639117f033b725fbbcc9570c3a7d4a7

See more details on using hashes here.

File details

Details for the file python_plot_mcp-1.0.3-py3-none-any.whl.

File metadata

File hashes

Hashes for python_plot_mcp-1.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 c0cd58f1400e30e79c2c248e3df924ce5f0c9d5b9ede0985a55181f1b006b677
MD5 600bcd5d1f6937022e5cd9071993d315
BLAKE2b-256 e66cf21c905dd76edef0819029ee7c41ef16c535cc4b186dedec2ddf1962a2d0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page