cockpit-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cockpit-mcp List all content models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
cockpit-mcp
A small, read-only MCP server for Cockpit CMS. It lets an AI agent understand the content behind a page — the models, fields, and types — by asking tools, instead of fetching the whole REST API or reading docs.
Generic and reusable: point it at any Cockpit v2 instance (Core or Pro) via env vars. Write it once, reuse in every project — the code is generic; only COCKPIT_URL + COCKPIT_TOKEN change per project.
Run with npx (no install)
It runs straight from GitHub — no clone, no registry:
npx -y github:Avanxo-Technology/cockpit-mcp # latest main
npx -y github:Avanxo-Technology/cockpit-mcp#v0.1.0 # pinned to a tagRelated MCP server: MCP Server for Database
Tools
Tool | What it does |
| List all content models (collections & singletons) with a one-line summary. Start here. |
| Field schema for one model — names, types, required, choices, linked models, nested fields. The "understand this quickly" tool. |
| List items for a model (Mongo-style |
| Fetch one item by |
| Case-insensitive substring match on a text field. |
All tools are GET-only; the server never mutates content.
Setup
cd cockpit-mcp
npm install
cp .env.example .env # then fill in COCKPIT_URL and COCKPIT_TOKENCreate the token in Cockpit admin: Settings → API → add token (a read scope is enough).
Register with opencode / Claude (stdio)
Example MCP client config:
{
"mcpServers": {
"cockpit": {
"command": "npx",
"args": ["-y", "github:Avanxo-Technology/cockpit-mcp"],
"env": {
"COCKPIT_URL": "http://localhost:8080",
"COCKPIT_TOKEN": "your-token-here"
}
}
}
}Each project registers the same package and supplies its own COCKPIT_URL / COCKPIT_TOKEN — one package, reused everywhere. (For local dev against a checkout, swap command to node with the path to src/index.js.)
The server logs a connection/health line to stderr on startup (never to stdout, which carries the JSON-RPC stream).
Compatibility
Targets Cockpit v2 (Core & Pro) REST API: GET /api/content/models, /api/content/items/{model}, /api/content/item/{model}/{id}, auth via the api-key header. On startup it probes list_models; if the URL/token is wrong it warns (auth failures surface as a clear message) and tools return errors until fixed — the server itself still starts.
Available Tools
5 toolsdescribe_modelA
Describe one content model's field schema (names, types, required, choices, linked models, nested fields). Use this to understand the exact shape of the data behind a page or component — instead of fetching the whole API or docs.
Inputs: model (required).
get_itemA
Get a single content item by its id. Read-only.
Inputs: id (required), model (required), fields, populate.
list_itemsA
List content items for a model. Supports an optional Mongo-style filter (JSON), sort, field projection, and limit. Read-only.
Inputs: model (required), skip, sort, limit, +3 more.
list_modelsA
List all Cockpit content models (collections & singletons) with a one-line summary each. Start here to see what content exists.
Inputs: no named parameters.
searchA
Find items in a model whose given text field matches a query (case-insensitive substring). Handy when you know the content but not the id.
Inputs: field (required), model (required), query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation: schema description, item retrieval by ID, filtered listing, model listing, and text search. No overlap in functionality.
Most tools use a clear verb_noun pattern (describe_model, get_item, list_items, list_models). 'search' deviates by omitting the noun but still follows the verb-first convention. Overall consistent.
Five tools is appropriate for a read-only content management server. Each tool serves a clear purpose without excess or deficiency.
The toolset fully covers the read-only domain: discover models, inspect schemas, retrieve items, and search. No gaps for the intended functionality.
Related MCP Connectors
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
Read-only search over 2,065+ AI agent tools and 276 MCP servers. Free, no sign-up needed.
Free, source-checked directory of AI agent tools, MCP servers and skills, with read-only search.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA read-only MCP server for AI coding agents to inspect repositories, audit code quality, route engineering skills, and plan safe issue/PR workflows.1MIT
- FlicenseNot gradedqualityDmaintenanceA read-only MCP server that enables AI agents to explore database schemas and execute safe queries on PostgreSQL and MySQL.-
- AlicenseAqualityDmaintenanceRead-only MCP server for self-hosted Confluence that lets AI agents search pages, fetch content, and navigate page trees via the REST API.55 npmMIT
- AlicenseAqualityBmaintenanceA read-only MCP server that enables AI agents to act as GCP platform engineers, allowing them to investigate incidents, take inventory, and find cost-optimization opportunities in Google Cloud projects without mutating any infrastructure.1622 PyPI2MIT