io.github.Kapeli/dash-mcp-server MCP Server
io.github.Kapeli/dash-mcp-server
Search 200+ API docsets in Dash directly from Claude and Cursor.
What is the io.github.Kapeli/dash-mcp-server MCP server?
The Dash MCP server provides tools to interact with Dash, the macOS API documentation browser. It enables searching across 200+ installed docsets, listing documentation sets, loading documentation pages, and enabling full-text search for specific docsets.
This server bridges Claude and Cursor with Dash, giving you instant access to API documentation without leaving your editor. Search across all your installed docsets, find code snippets, and load full documentation pages directly into your AI conversations.
How to install io.github.Kapeli/dash-mcp-server
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
list_installed_docsets— Lists all installed documentation sets in Dashsearch_documentation— Searches across docsets and snippetsload_documentation_page— Loads a documentation page from a load_url returned by search_documentationenable_docset_fts— Enables full-text search for a specific docset
Use cases
- Search API documentation across 200+ docsets without switching apps
- Find code snippets and examples from installed documentation
- Load full documentation pages into Claude for detailed reference
- Enable full-text search on specific docsets for deeper exploration
- Quickly reference API syntax and parameters while coding
io.github.Kapeli/dash-mcp-server MCP server FAQ
It's an MCP server that connects Claude and Cursor to Dash, the macOS documentation browser, allowing you to search and access 200+ API docsets directly from your AI conversations.
Yes, Dash 8 or higher must be installed on macOS. You can download it at https://blog.kapeli.com/dash-8.
Add this to your claude_desktop_config.json: {"dash-api": {"command": "uvx", "args": ["--from", "git+https://github.com/Kapeli/dash-mcp-server.git", "dash-mcp-server"]}}
Run: claude mcp add dash-api -- uvx --from "git+https://github.com/Kapeli/dash-mcp-server.git" "dash-mcp-server"
macOS with Dash 8+ installed, Python 3.11.4 or higher, and uv (installable via brew install uv).
The MCP server is free and open-source. Dash itself is a paid application available at https://kapeli.com/dash.
README (reference)
Source of truth, from the repository.
mcp-server-dash
A Model Context Protocol (MCP) server that provides tools to interact with the Dash documentation browser API.
Dash 8 is required. You can download Dash 8 at https://blog.kapeli.com/dash-8.
mcp-name: io.github.Kapeli/dash-mcp-server
<a href="https://glama.ai/mcp/servers/@Kapeli/dash-mcp-server"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@Kapeli/dash-mcp-server/badge" alt="Dash Server MCP server" /> </a>Overview
The Dash MCP server provides tools for accessing and searching documentation directly from Dash, the macOS documentation browser. MCP clients can:
- List installed docsets
- Search across docsets and code snippets
- Load documentation pages from search results
- Enable full-text search for specific docsets
Notice
This is a work in progress. Any suggestions are welcome!
Tools
- list_installed_docsets
- Lists all installed documentation sets in Dash
- search_documentation
- Searches across docsets and snippets
- load_documentation_page
- Loads a documentation page from a
load_urlreturned bysearch_documentation
- Loads a documentation page from a
- enable_docset_fts
- Enables full-text search for a specific docset
Requirements
- macOS (required for Dash app)
- Dash installed
- Python 3.11.4 or higher
- uv
Configuration
Using uvx
brew install uv
in claude_desktop_config.json
{
"mcpServers": {
"dash-api": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Kapeli/dash-mcp-server.git",
"dash-mcp-server"
]
}
}
}
in Claude Code
claude mcp add dash-api -- uvx --from "git+https://github.com/Kapeli/dash-mcp-server.git" "dash-mcp-server"
Related MCP servers

io.github.Karniej/vidnotes
Turn any video into transcripts, summaries, chapters, and comparisons for your AI agent.
Generate design systems: OKLCH color palettes, fluid type scales, spacing, shape and icon tokens.

TestAtlas
Semantic map of a .NET test-automation solution for AI agents — search, impact, endpoints
Multi-agent collaborative reasoning with auditable thought ledgers, persistent storage, and real-time observability.

io.github.KatoMato65/time-mcp
Simple MCP server that tells the time
Git-aware safe file ops for AI agents: delete anything except git-tracked source code.


