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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.