mcp-cvp-fun
Documentation
MCP Server Demo with Arista CloudVision
> [!WARNING]
> Please note that this is not officially supported by Arista.
>
> You might not want to do this in your production environment as it is not using a local LLM.
>
> The free plan of Claude might cause anxiety!
Kudos to @burnyd for the inspiriation and for writing this blog post: https://danielhertzberg.net/posts/mcp-servers/
Expanding on that, I've added a few more API calls to be able to ask Claude to get connectivity monitor data, and create tags for Studios and dashboards, but obviously any API call can be added very easy with the `@mcp.tool()` decorator.
To learn more about MCP please visit https://modelcontextprotocol.io/introduction.
Example usage
1\. Create a .env file like the following.
CVPTOKEN="Insert CloudVision Service account token here"
CVP="www.arista.io"2\. Download Claude Desktop
3\. In Claude's developer settings update the claude_desktop_config.json and tell it to run your script like below:
{
"mcpServers": {
"CVP MCP Server": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"/home/ansible/mcp-cvp-fun/mcp_server_rest.py"
]
}
}
}4\. Reload Claude and start prompting

How to generate service account tokens
Service accounts can be created from the Settings page where a service token can be generated as seen below:



Frequently asked questions
What is mcp-cvp-fun?
mcp-cvp-fun is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install mcp-cvp-fun?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-cvp-fun open source?
Yes — it is hosted on GitHub at https://github.com/noredistribution/mcp-cvp-fun and has 2 stars.
Related MCP tools
5. Update .env file in the root directory with your mem0 API key: for the Model Context Protocol. Enhance AI assistants with powerful integrations.
Model Context Protocol integration for Python. Enhance AI assistants with powerful Python-based capabilities and integration support.
This repository contains Model Context Protocol (MCP) servers that enable MCP clients (like Claude Desktop or the cline.
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP