dittu-mcp
Phone-camera + Bluetooth remote control for any computer, exposed as an MCP server for Claude, Cursor and other AI assistants
Documentation
Dittu MCP Server
Dittu turns a phone into the eyes and hands of an AI assistant. Stand the phone on a tripod
facing a monitor — the camera reads the screen, Bluetooth pairs as a real mouse and keyboard.
No software to install on the target computer, no remote-desktop setup.
- Website: https://dittu.org
- Setup instructions (Claude Desktop / Claude Code / Cursor / ChatGPT): https://dittu.org/setup
- Remote MCP endpoint: `https://app.dittu.org/mcp` (streamable-http, `Authorization: Bearer `)
- Get an API key: register a device in the Dittu Android app — https://play.google.com/store/apps/details?id=com.dittu
Tools
| Tool | What it does | Output | When to use |
|---|---|---|---|
| `take_screenshot` | Captures what the phone's camera currently sees on the monitor | Image | Before any action, to check current screen state |
| `take_screenshot_with_grid` | Same as `take_screenshot` but overlays a coordinate grid | Image | To locate exact click targets by coordinate |
| `take_screenshot_with_crosshair(nx, ny)` | Zoomed crop around a point with a crosshair marking the target | Image | To verify the cursor will land exactly where intended, before clicking a small/important target |
| `get_raw_screenshot` | Unprocessed camera frame, no corner-mapping applied | Image | Debugging camera alignment issues |
| `move_mouse(nx, ny)` | Moves the cursor to a normalized screen coordinate without clicking | Confirmation | Positioning the cursor before a verified click |
| `click(nx, ny)` | Left-clicks at a normalized screen coordinate | Confirmation | Standard click actions |
| `double_click(nx, ny)` | Double left-clicks at a normalized screen coordinate | Confirmation | Opening files/apps, other double-click actions |
| `scroll` | Scrolls the screen in a given direction | Confirmation | Navigating long pages or lists |
| `key` | Sends a keyboard key or shortcut | Confirmation | Shortcuts, Enter, Escape, arrow keys, etc. |
| `type_text` | Types a string of text via the Bluetooth keyboard | Confirmation | Filling in text fields, search boxes, documents |
| `get_corners` | Reads the current four-corner monitor calibration | Coordinates | Diagnosing why clicks land off-target |
| `set_corners` | Sets the four-corner monitor calibration | Confirmation | Fixing calibration when the camera view is misaligned or cropped |
Why a camera instead of screen-sharing?
Because it works on any computer — no software to install, no permissions to configure, no
remote-desktop setup. If the monitor is in front of the phone, an AI assistant can see it and
control it.
Built for
- Automating repetitive desktop tasks
- Controlling a computer you can't install anything on
- Letting an AI assistant actually do things on-screen, not just describe them
Frequently asked questions
What is dittu-mcp?
dittu-mcp is Phone-camera + Bluetooth remote control for any computer, exposed as an MCP server for Claude, Cursor and other AI assistants
How do I install dittu-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is dittu-mcp open source?
Yes — it is hosted on GitHub at https://github.com/BorisGujvin/dittu-mcp.
Related MCP tools
wigoloThe go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
OpenOSINTAI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
memoraGive your AI agents persistent, collective memory — with deduplicating absorb, supersession lineage, semantic search, and a graph UI. Speaks MCP.
firecrawl-mcp-server🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Unity-MCPAI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for free.
jcodemunch-mcpCut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP