{"id":"runablehq-mobile-mcp","name":"mobile-mcp","homepage":null,"repo_url":"https://github.com/runablehq/mobile-mcp","category":"automation","subcategories":[],"tags":["mcp","mobile-automation","android","adb","claude","nodejs","typescript","ui-dumps","ai-agents"],"what_it_does":"mobile-mcp is an MCP server intended to let LLMs control Android mobile devices via structured UI dumps, using Node.js/TypeScript tooling and ADB for connectivity.","use_cases":["LLM-assisted Android UI automation where text/UI state is preferred over screenshots","Interactive mobile testing or debugging flows driven by an agent through MCP tools","Building agentic mobile workflows (navigation, taps, form filling) on Android devices/emulators"],"not_for":["iOS automation (explicitly not supported yet)","Production-grade automation at scale without additional operational hardening","Scenarios requiring a documented public REST/GraphQL/SDK interface beyond MCP"],"best_when":"You have an Android device/emulator available with ADB and want to integrate with an MCP-capable client (e.g., Claude Desktop / VS Code MCP).","avoid_when":"You need iOS support, a hosted cloud API, or well-documented reliability/error semantics for automated execution at high volume.","alternatives":["Custom MCP server wrapping existing Android automation tooling (e.g., Appium / UIAutomator) with your own contracts","Appium directly (non-MCP) with an LLM acting as planner/operator","Browser automation-style approaches adapted for mobile UI (less direct than UI-dump-driven automation)"],"af_score":44.8,"security_score":45.2,"reliability_score":25.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:55:29.627861+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication mechanism is described in the provided README/manifest; usage appears local (npx/CLI) talking to a connected device via ADB."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided; npm package usage suggests self-hosted/local automation rather than a hosted paid API."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":44.8,"security_score":45.2,"reliability_score":25.0,"mcp_server_quality":55.0,"documentation_accuracy":45.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":0.0,"tls_enforcement":100.0,"auth_strength":40.0,"scope_granularity":0.0,"dependency_hygiene":35.0,"secret_handling":50.0,"security_notes":"No hosted network service or auth details are described; interactions appear local via npx/CLI and ADB. TLS/auth scope granularity cannot be confirmed from provided content. Dependency hygiene and secret handling are not verifiable from the provided README/manifest.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":30.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Only Android is supported per README; agents attempting iOS flows should fail.","Requires working ADB/Android Studio setup and a reachable emulator/physical device.","UI-dump-based automation may require agent understanding of device state and potential timing/latency issues (not documented)."]}}