CloudVision MCP Server
Enables querying and interacting with Arista CloudVision via MCP, supporting both HTTP and gRPC connections.
README
MCP Server for CloudVision
This MCP server can be used to query and interact with Arista CloudVision.
Usage
To run, you can the server via uv. Make sure you load your environment variables for CVP and CVPTOKEN prior to running.
uv run --env-file cvp-mcp.env cloudvision_mcp.py
Alternate Method
To run in a container, build the image first.
podman build -t cloudvision_mcp:latest .
Populate an env-file, sample below.
cvp-mcp.env
CVP=<cvp_server_address>
CVPTOKEN=<service_account_api_token>
CERT=<cert_file_name>
Note The Cert file is only necessary if you are connecting to an on-prem CVP instance with self-signed certs
Run
podman run -d --name cvp-mcp -p 8000:8000 --env-file cvp-mcp.env cloudvision-mcp:latest
The server will be running by default with Streamable HTTP on port 8000
Server Options
The server can be configured with the following flags
| Flag | Description |
|---|---|
| -t | MCP Transport {"http", "stdio"} (default=http) |
| -p | MCP Port for Streamable HTTP (default=8000) |
| -c | CVP Connection protocol {"grcp", "http"} (default=grpc) |
| -d | Enable debug logging |
Note
For gRPC connections, a trusted cert mut be running on CloudVision. Otherwise, you will need to have a copy of the self-signed cert in the project directory before building the container image. The cert file should be named cert.pem
Client Configurations
The example client configs can work with Claude Desktop or a local Ollama LLM via (https://github.com/jonigl/mcp-client-for-ollama) project.
STDIO MCP Server Configuration
{
"mcpServers": {
"CVP MCP Server": {
"command": "uv",
"args": [
"run",
"--directory",
"<path_to_project_directory>",
"./cloudvision_mcp.py"
]
}
}
}
Streamable HTTP Server Configuration
{
"mcpServers": {
"CVP MCP Server": {
"type": "streamable_http",
"url": "<mcp_server_address>:<port>/mcp"
}
}
}
Streamable HTTP Server Configuration (Claude Desktop)
{
"mcpServers": {
"CVP MCP Server": {
"command": "npx",
"args": [
"mcp-remote",
"http://<mcp_server_address>:<port>/mcp",
"--allow-http"
]
}
}
}
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.