Nextcloud Developer Documentation MCP
Provides tools for searching and retrieving Nextcloud developer documentation, including full-text search, content retrieval, and question answering with references.
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., "@Nextcloud Developer Documentation MCPsearch Nextcloud app development best practices"
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.
Nextcloud Developer Documentation MCP (Docker)
This project provides a Dockerized MCP server that fetches and indexes one or more documentation source URLs recursively, then exposes MCP tools for coding agents. The first configured sources are:
https://github.com/nextcloud-deps/ocp(full repo, recursive)https://github.com/nextcloud/documentation/tree/master/developer_manual(subtree, recursive)https://github.com/nextcloud/server/blob/master/openapi.jsonhttps://github.com/nextcloud-libraries/nextcloud-vue(upstream source fornode_modules/@nextcloud/vue)
The nextcloud-developer-documentation-mcp container runs as a persistent HTTP MCP service on http://localhost:8000/nextcloud-developer-documentation-mcp.
On every container start, all configured source URLs are refreshed and the index is rebuilt
before the server begins accepting MCP requests.
The intended end-user configuration is minimal:
run
docker compose up -d nextcloud-developer-documentation-mcppoint your coding agent to
http://localhost:8000/nextcloud-developer-documentation-mcp
MCP tools
search_docs(query, top_k=5)Full-text search over indexed files from all configured source URLs.
get_doc(path, chunk=None, max_chars=12000)Fetch full content (chunked) for an indexed file path.
answer_docs(question, top_k=6)Retrieval-based answer with references.
refresh_index()Pull latest state for all configured source URLs and rebuild index.
docs_health()Health/index metadata.
list_indexed_files(limit=200, offset=0, prefix=None)Lists indexed file paths for validation (supports pagination and prefix filtering).
Related MCP server: Markdown RAG MCP
What gets indexed
By default, these file extensions are indexed from all configured source URLs:
.md,.php,.rst,.txt,.yml,.yaml,.json,.js,.ts,.vue,.css,.scss
The index is a SQLite FTS5 database persisted in a Docker volume (nextcloud-docs-data).
Run with Docker Compose
Start the persistent HTTP MCP server:
docker compose up -d nextcloud-developer-documentation-mcpAdd to coding agents (like Claude Code)
Point the agent at the running HTTP MCP endpoint:
{
"mcpServers": {
"nextcloud-developer-documentation": {
"url": "http://localhost:8000/nextcloud-developer-documentation-mcp"
}
}
}Add to coding agent Codex App
[mcp_servers.nextcloud_developer_documentation]
url = "http://localhost:8000/nextcloud-developer-documentation-mcp"
enabled = trueAgents that support HTTP MCP can use the same endpoint directly.
This server cannot be deployed
Maintenance
Related MCP Connectors
Query any docs site via MCP. Submit a URL, ask questions, get cited answers.
MCP server for querying Forkast documentation
Agentic search over your Dewey document collections from any MCP-compatible client.
- docs2mcpOAuthcom.docs2mcp
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceIndexes documentation sites by base URL and serves keyword search, optional semantic search, and Markdown page retrieval as MCP tools, all from a single SQLite file.-
- AlicenseNot gradedqualityDmaintenanceProvides semantic search over markdown documentation using RAG, allowing natural language queries and integration with MCP clients.1MIT
- FlicenseNot gradedqualityDmaintenanceScrapes, stores, and searches documentation locally, enabling AI assistants to access and query documentation via MCP.4-
- FlicenseAqualityCmaintenanceEnables searching documentation from GitHub repositories and web pages via MCP tools, with in-memory indexing and caching for fast retrieval.3-