Nextcloud Developer Documentation MCP
Provides MCP tools for searching, retrieving, and answering questions about indexed Nextcloud developer documentation from multiple sources.
README
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.json
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-mcp - point 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).
What gets indexed
By default, these file extensions are indexed from all configured source URLs:
.md,.php,.rst,.txt,.yml,.yaml,.json
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-mcp
Add 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 = true
Agents that support HTTP MCP can use the same endpoint directly.
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.