{"id":"alanisme-adb-tui","name":"adb-tui","homepage":null,"repo_url":"https://github.com/alanisme/adb-tui","category":"devtools","subcategories":[],"tags":["adb","android-debugging","tui","mcp","model-context-protocol","ai-tools","terminal-ui","automation","go","wireless-adb"],"what_it_does":"adb-tui is a Go-based Android debugging terminal UI (TUI) and an MCP server that exposes broad Android Debug Bridge (ADB) functionality as AI-agent tools (stdio and HTTP/SSE transports). It also provides a scriptable CLI for common ADB operations (devices, shell, screenshot, install, and starting MCP).","use_cases":["Interactive Android debugging in a terminal (devices, shell, logcat, files, packages, processes, settings, performance).","AI/agent-driven Android automation via MCP tools (install apps, read/filter logcat, push/pull files, screenshots/screen recording, UI element tapping).","Headless/CI-style remote inspection using wireless ADB plus MCP over HTTP/SSE.","Automated testing and exploration (monkey/instrumentation, UI hierarchy queries, take screenshots).","Device fleet management (connect/disconnect multiple devices; view info/battery/network)."],"not_for":["Production-grade security gateways or multi-tenant remote administration without additional access controls.","Environments where exposing powerful device-control tools to an AI agent is unacceptable (e.g., untrusted agent/LLM).","Use cases that require a fully documented REST/JSON API with stable schemas beyond MCP tooling.","Users who cannot access an ADB-compatible environment (ADB installed and device connectivity)."],"best_when":"You want an interactive terminal dashboard and/or an MCP tool endpoint to let an AI agent drive Android debugging and automation on devices you control.","avoid_when":"You need strong authentication/authorization boundaries for remote access, or you plan to grant tool access to untrusted parties/agents without network isolation and strict operational safeguards.","alternatives":["Other ADB frontends and terminals (e.g., scrcpy for screen/mouse/keyboard streaming).","MCP tool servers that wrap ADB (custom/third-party) if you need tighter security controls.","Direct ADB scripting (shell scripts) for deterministic workflows.","General-purpose Android automation frameworks (e.g., Appium) for UI testing (different tradeoffs)."],"af_score":52.5,"security_score":39.8,"reliability_score":26.2,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:53:36.499758+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":["None stated for MCP/HTTP transport (not documented in README)."],"oauth":false,"scopes":false,"notes":"The README does not describe any authentication/authorization for the MCP server (stdio or HTTP/SSE). If HTTP/SSE is exposed beyond localhost, strong network isolation and/or external auth is needed to prevent unauthorized device control."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source; no pricing information provided in README."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":52.5,"security_score":39.8,"reliability_score":26.2,"mcp_server_quality":85.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":35.0,"rate_limit_clarity":0.0,"tls_enforcement":40.0,"auth_strength":25.0,"scope_granularity":30.0,"dependency_hygiene":50.0,"secret_handling":60.0,"security_notes":"Security claims are mostly at the ADB-command level (README says parameterized execution/no injection vectors). However, the README does not document authentication/authorization for MCP/HTTP/SSE, nor TLS requirements for that transport, nor scope/permissioning for tools. The tool set includes high-impact operations (shell/root actions, app install/remove, input injection, settings/security changes), so robust external controls (network isolation, least-privilege wrapping, allowlisting, and operational safeguards) are important. No evidence is provided about dependency vulnerabilities or secret handling behavior beyond general best practices.","uptime_documented":0.0,"version_stability":35.0,"breaking_changes_history":30.0,"error_recovery":40.0,"idempotency_support":"false","idempotency_notes":"README does not discuss idempotency guarantees for MCP tools; many tools are inherently side-effecting (install, input, settings).","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Tools can cause irreversible/side-effecting changes on the device (install/uninstall, shell commands, taps/input, settings). Require careful agent prompting and/or manual approval workflows.","If HTTP/SSE transport is bound to a non-local interface, agents may be able to access the tool endpoint; ensure network isolation and external auth/allowlisting.","MCP tool availability and behavior may depend on device state (rooting, permissions, connectivity, wireless debugging)."]}}