{"slug": "mcp-server-runs-on-android", "title": "MCP server runs on Android", "summary": "An open-source MCP server that runs on Android and exposes tap, type, scroll, and screenshot actions to AI agents has been released on GitHub, with a FOSS build heading to F-Droid. The app, which registers as an accessibility service, includes on-device privacy redaction that strips personal data before sending context to LLM providers, and it integrates with Claude and ChatGPT via its own OAuth server. Typical interactions consume 200-400 tokens per step, and privacy detection accuracy is around 87%.", "body_md": "# MCP server runs on Android\n\n[MCP](/en/tags/mcp/), an MCP server that runs directly on your phone and exposes tap, type, scroll, and screenshot actions to any compatible agent. I've been testing it for a few weeks now, and the practical implications for AI workflow automation are genuinely interesting.\n\n**How it works in practice**\n\nThe app registers as an accessibility service, which gives it read access to the UI hierarchy across all installed apps. When an agent sends a tool call — say, \"open Gmail and search for 'invoice'\" — the server parses the accessibility tree, finds the relevant elements, and executes the sequence. Token usage stays low because the server returns structured summaries instead of raw XML dumps. A typical interaction consumes roughly 200-400 tokens per step depending on screen complexity.\n\n**Privacy mode is the standout feature**\n\nAfter early feedback made it clear nobody wants their full screen context shipped to an LLM provider, the author added on-device redaction. A small local model combined with deterministic regex detectors strips emails, phone numbers, credit cards, IBANs, national IDs, and English names before anything leaves the device. Benchmarked detection sits around 87% — non-English names remain the weak spot, but a custom model is in development. For anyone building LLM agent pipelines that touch personal data, this approach deserves attention.\n\n**Integration with Claude and ChatGPT**\n\nThe app acts as its own OAuth server. You approve connections via a code displayed on the phone, then point [Claude](/en/tags/claude/).ai, Claude Desktop, or chatgpt.com at the local endpoint. No ngrok, no Cloudflare tunnel — though a free reverse tunnel with Let's Encrypt certificates and true end-to-end encryption is on the roadmap to replace those workarounds entirely.\n\n**Tradeoffs worth knowing**\n\n- Google Play distribution is impossible because accessibility services trigger policy restrictions. The APK lives on GitHub; a FOSS build without Play Services is heading to F-Droid soon.\n- Prompt injection mitigation: every response from the server is prefixed with a strong untrusted-input warning. Not bulletproof, but it raises the bar significantly.\n- App coverage varies. Mainstream apps (Chrome, Gmail, Maps, Spotify) work reliably. Custom or heavily obfuscated UIs sometimes break the tree traversal.\n\n**What's coming next**\n\n- Skills database per app so agents can plan faster without trial-and-error exploration\n- Custom privacy model for better non-English name detection\n- Guided setup flow and revised UI to lower the barrier for non-technical users\n\nIf you're experimenting with AI workflow automation on mobile, this is worth a hands-on guide session. The repo includes a practical tutorial for getting started from scratch, and even smaller models like Haiku can drive meaningful multi-step tasks when given enough context.\n\n[Why most companies will miss the AI-native shift entirely 4h ago](/en/news/6912/)\n\n[Claude just fired its first human employee 20h ago](/en/news/6832/)\n\n[Free API keys for top models are now public 21h ago](/en/news/6826/)\n\n[Finding clean open source alternatives to AI-tainted software is 1d ago](/en/news/6736/)\n\n[Will Gen Z actually survive the AI takeover of entry-level roles? 1d ago](/en/news/6721/)\n\n[Codex weekly limits are disappearing way too fast for me 1d ago](/en/news/6708/)\n\n[Next Anders Hejlsberg just dropped a talk that should make every →](/en/news/6939/)", "url": "https://wpnews.pro/news/mcp-server-runs-on-android", "canonical_source": "https://promptcube3.com/en/news/6941/", "published_at": "2026-08-19 15:15:19+00:00", "updated_at": "2026-08-19 15:44:00.476909+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools"], "entities": ["MCP", "GitHub", "F-Droid", "Claude", "ChatGPT", "Google Play"], "alternates": {"html": "https://wpnews.pro/news/mcp-server-runs-on-android", "markdown": "https://wpnews.pro/news/mcp-server-runs-on-android.md", "text": "https://wpnews.pro/news/mcp-server-runs-on-android.txt", "jsonld": "https://wpnews.pro/news/mcp-server-runs-on-android.jsonld"}}