mcp-caddy
Enables management of Caddy web server via admin API, allowing inspection of routes, upstream health, certificates, and configuration reloading.
README
mcp-caddy
MCP server for Caddy web server management. Exposes 7 tools for inspecting routes, upstream health, certificates, and reloading configuration via the Caddy admin API.
Quick Start
With uvx (recommended):
CADDY_HOST=http://10.0.0.31:2019 uvx mcp-caddy
With Docker:
docker run -i \
-e CADDY_HOST=http://10.0.0.31:2019 \
ghcr.io/aaronckj/mcp-caddy:latest
Add to Claude Code:
claude mcp add caddy -s user -e CADDY_HOST=http://10.0.0.31:2019 -- uvx mcp-caddy
Configuration
| Variable | Required | Default | Description |
|---|---|---|---|
CADDY_HOST |
No | http://localhost:2019 |
Caddy admin API URL |
CADDY_TIMEOUT |
No | 30 |
HTTP timeout in seconds |
Finding Your CADDY_HOST
The Caddy admin API binds to localhost:2019 by default. Depending on your setup:
- MCP server on same host as Caddy → use the default
http://localhost:2019 - Caddy in Docker, MCP server on the same Docker host → add
ports: ["127.0.0.1:2019:2019"]to your Caddy compose service, then usehttp://localhost:2019 - Remote Caddy host → SSH tunnel:
ssh -L 2019:localhost:2019 user@caddy-host, then usehttp://localhost:2019 - Caddy exposes admin via reverse proxy → set
CADDY_HOST=https://caddy-admin.example.com
The Caddy admin API has no authentication by default. If you expose it beyond localhost, add Caddy basic auth to that route.
Tools
| Tool | Description |
|---|---|
server_info |
Caddy version and loaded modules |
get_config |
Full configuration as JSON |
list_routes |
All virtual hosts with upstream targets |
list_upstreams |
Upstream proxy health status |
get_certificates |
TLS automation policies and ACME issuers |
adapt_config |
Convert a Caddyfile snippet to JSON |
reload |
Reload config from a JSON string or file path |
Development
git clone https://github.com/aaronckj/mcp-caddy
cd mcp-caddy
uv sync --extra dev
uv run pytest -v
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.