cml2-mcp
Thin MCP server for Cisco CML2 that exposes the live OpenAPI specification and a generic API call tool, enabling models to interact with CML2 by reading the spec first.
README
cml2-mcp
Thin MCP server for Cisco CML2.
It deliberately avoids mirroring the CML API as typed (Pydantic) tools — every prior generation that did so broke when the controller shipped a schema change. Instead this server exposes only:
cml_openapi(refresh=False)— fetch CML's liveopenapi.json(cached 24 h).cml_api(method, path, body=None)— generic authenticated REST call after/api/v0. Re-authenticates and retries once on HTTP 401.- Resource
cml://openapi.json— same content ascml_openapi().
The model is expected to read the OpenAPI spec first and then craft calls.
Configuration
Required environment:
| Var | Example |
|---|---|
CML_URL |
https://cml.example.net/ |
CML_USERNAME |
admin |
CML_PASSWORD |
… |
Optional:
CML_VERIFY_SSL=true— verify TLS (default: off; CML often uses self-signed certs).CML_CACHE_DIR— token / openapi cache directory (default:~/.cache/cml/).
The token is written to $CML_CACHE_DIR/token with mode 0600.
Running
With uv directly from the source tree:
uv run cml2-mcp
After publishing to PyPI (or via uv tool install .):
uvx cml2-mcp
Claude Desktop / Claude Code registration
Wrap the command so the password is fetched from a secure store rather than appearing in plain text. Example with macOS Keychain:
{
"mcpServers": {
"cml2": {
"command": "sh",
"args": [
"-c",
"CML_PASSWORD=$(security find-generic-password -a <account> -s <service> -w) exec uvx cml2-mcp"
],
"env": {
"CML_URL": "https://cml.example.net/",
"CML_USERNAME": "admin"
}
}
}
}
For Claude Code:
claude mcp add cml2 -- sh -c 'CML_PASSWORD=$(security find-generic-password -a <account> -s <service> -w) exec uvx cml2-mcp'
(Set CML_URL / CML_USERNAME in the same env or via claude mcp add ... -e KEY=VAL.)
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.