Mist MCP Server
Provides reliable access to Juniper Mist from AI tools like Cursor and VS Code, enabling natural language interaction with Mist API without writing code.
README
Mist MCP Server
Reliable access to Juniper Mist from your AI tools, without writing code.
This project provides a production-grade MCP server that wraps the Mist API via
mistapi, so Cursor and VS Code can call Mist safely through standard MCP
tools.
Why this exists
MCP servers make API access simple and consistent for AI tools. This server centralizes connection and auth, validates configuration at startup, and exposes a tool registry so non-coders can use Mist through natural language.
Prerequisites
- Python 3.10+
- A Mist API token
Install
No manual install required for end users. The MCP runner bootstraps the local virtual environment on first run.
Configure
Create a .env file in this folder (see mist.env.example):
MIST_API_TOKEN=your_token_here
MIST_API_HOST=https://api.mist.com
MIST_API_TIMEOUT_SECONDS=30
Important: MIST_API_HOST must be the base host (no /api/v1). The server
will call the Mist “self” endpoint at startup and exit immediately if the host
or token is invalid.
Local use (Cursor)
- Open this project in Cursor.
- Make sure a
mcp.jsonfile exists at.cursor/mcp.json. This repo already provides it, so you usually do not need to change anything. - Use the configuration below:
{
"mcpServers": {
"mist": {
"command": "${workspaceFolder}/run-mcp.sh",
"args": [],
"envFile": "${workspaceFolder}/.env",
"transport": "stdio"
}
}
}
- Restart Cursor (or reload the window).
- Ask Cursor to call Mist tools, e.g. “list my orgs”.
Local use (VS Code)
- Open this project in VS Code.
- Make sure a
mcp.jsonfile exists at.vscode/mcp.json. This repo already provides it, so you usually do not need to change anything. - Reload the window and use your MCP client to call Mist tools.
Usage
- A tool registry is generated from the Mist SDK.
- Use
mist_search_toolsto find tools by keyword. - Use
mist_list_groupsto discover tool groups and filter search. - Use
mist_list_methodsto list methods in a group. - Use
mist_describe_toolto see parameters and details. - Use
mist_call_toolto execute by name with args/kwargs. - Regenerate the registry after SDK updates via
scripts/generate_tools.py.
Sponsored by Hamina
<a href="https://www.hamina.com/"> <img src="assets/hamina-logo.svg" alt="Hamina logo" width="240" height="50"/> </a>
Built while working at Hamina.
Development
pip install -e ".[dev]"
./.venv/bin/python scripts/generate_tools.py
pytest
ruff check .
ruff format .
mypy src
Contributing
We welcome good PRs. See CONTRIBUTING.md for guidelines.
License
Apache-2.0. See LICENSE.
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。