adb_crash_logs
Read ANR (Application Not Responding) traces and tombstone crash dumps from the device. Requires root access for /data/anr/ and /data/tombstones/. Returns the most recent entries.
This record as markdown: /tools/io-github-fullread-deepadb/adb-crash-logs.md
What adb_crash_logs does on Deepadb
AI agents call adb_crash_logs to retrieve information from Deepadb without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why adb_crash_logs is rated Low
This is a Read operation that retrieves existing crash logs and ANR traces without modifying or deleting data. However, severity is elevated to 'high' because crash logs often contain sensitive information including stack traces, memory layouts, private process states, and potentially user data, which could be used for reconnaissance or exploitation if obtained by an adversary through agent misuse.
From the tool's definition Tool description states 'Read ANR traces and tombstone crash dumps from the device' — explicitly a read operation that retrieves crash and diagnostic logs.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs adb_crash_logs safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Deepadb, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For adb_crash_logs, this is the rule to start with:
adb_crash_logs is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Deepadb, apply this rule, and every adb_crash_logs call is checked against it from then on.
Questions about adb_crash_logs
Read ANR (Application Not Responding) traces and tombstone crash dumps from the device. Requires root access for /data/anr/ and /data/tombstones/. Returns the most recent entries. It is categorised as a Read tool in the Deepadb MCP Server, which means it retrieves data without modifying state.
Register the Deepadb MCP server in PolicyLayer and add a rule for adb_crash_logs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Deepadb. Nothing to install.
adb_crash_logs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the adb_crash_logs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for adb_crash_logs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
adb_crash_logs is provided by the Deepadb MCP server (deepadb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deepadb, and thousands of servers like it.
This server
Across the catalogue