# adb_ci_run_tests Run Android instrumented tests (androidTest) via Agent View of the PolicyLayer registry record for `adb_ci_run_tests`. HTML page: https://policylayer.com/tools/io-github-fullread-deepadb/adb-ci-run-tests ## Facts - Tool: `adb_ci_run_tests` - Server: Deepadb (`deepadb`) — https://policylayer.com/tools/io-github-fullread-deepadb.md - Install: `npx -y deepadb` - Homepage: https://github.com/fullread/DeepADB - Risk category: Execute (High risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 0 - Recommended policy verdict: Rate-limited ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "adb_ci_run_tests", "arguments": {} } } ``` ## Why adb_ci_run_tests is rated High The tool executes code (Android instrumented tests) on a device, which is an Execute-category action. Severity is high because malicious test payloads could modify device state, exfiltrate data, or cause system instability, though the blast radius is limited to the connected device and the scope of Android testing frameworks. From the tool's own definition: "adb_ci_run_tests: 'Run Android instrumented tests (androidTest) via' — the word 'Run' combined with 'tests' indicates execution of arbitrary test code on a connected Android device." ## Use case AI agents invoke adb_ci_run_tests to trigger actions in Deepadb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Deepadb: ```json { "version": "1", "default": "deny", "tools": { "adb_ci_run_tests": { "limits": [ { "counter": "adb_ci_run_tests_rate", "window": "minute", "max": 10, "scope": "grant" } ] } } } ``` ## Other tools on Deepadb (204) - `adb_clear_data` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-clear-data.md - `adb_file_move` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-file-move.md - `adb_forward_remove` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-forward-remove.md - `adb_logcat_clear` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-logcat-clear.md - `adb_qemu_images` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-qemu-images.md - `adb_result_drop` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-result-drop.md - `adb_reverse_remove` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-reverse-remove.md - `adb_rm` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-rm.md - `adb_tunnel_close` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-tunnel-close.md - `adb_uninstall` — Destructive — https://policylayer.com/tools/io-github-fullread-deepadb/adb-uninstall.md - `adb_a11y_audit` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-a11y-audit.md - `adb_airplane_cycle` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-airplane-cycle.md - `adb_airplane_mode` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-airplane-mode.md - `adb_at_batch` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-at-batch.md - `adb_at_probe` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-at-probe.md - `adb_at_send` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-at-send.md - `adb_batch_actions` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-batch-actions.md - `adb_build_and_install` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-build-and-install.md - `adb_ci_wait_boot` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-ci-wait-boot.md - `adb_connect` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-connect.md - `adb_disconnect` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-disconnect.md - `adb_dumpsys` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-dumpsys.md - `adb_emulator_start` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-emulator-start.md - `adb_emulator_stop` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-emulator-stop.md - `adb_farm_run` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-farm-run.md - `adb_file_chmod` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-file-chmod.md - `adb_file_chown` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-file-chown.md - `adb_force_stop` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-force-stop.md - `adb_forward` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-forward.md - `adb_gradle` — Execute — https://policylayer.com/tools/io-github-fullread-deepadb/adb-gradle.md - …and 174 more: https://policylayer.com/tools/io-github-fullread-deepadb.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-fullread-deepadb · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-fullread-deepadb