adb_a11y_audit
Run an automated accessibility audit on the current screen. Checks for: missing labels on interactive elements, undersized touch targets (<48dp), images without content-descriptions, clickable elements missing focusability, and duplicate descriptions. Returns a structured report with severity and...
This record as markdown: /tools/io-github-fullread-deepadb/adb-a11y-audit.md
What adb_a11y_audit does on Deepadb
AI agents invoke adb_a11y_audit 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.
Why adb_a11y_audit is rated High
This tool executes an accessibility audit scan whose effects depend on the current screen state and configuration. While read-like in that it inspects rather than modifies data, the audit itself is an active operation that executes checks and generates results. It does not destructively modify data, nor does it have financial impact.
From the tool's definition Tool executes an automated audit that 'runs' accessibility checks on the current screen and returns structured analysis. The description indicates active analysis/inspection of UI state triggered by tool invocation.
Attacks that exploit this kind of access
The rule that runs adb_a11y_audit 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_a11y_audit, this is the rule to start with:
adb_a11y_audit stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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_a11y_audit call is checked against it from then on.
Questions about adb_a11y_audit
Run an automated accessibility audit on the current screen. Checks for: missing labels on interactive elements, undersized touch targets (<48dp), images without content-descriptions, clickable elements missing focusability, and duplicate descriptions. Returns a structured report with severity and rule violations. It is categorised as a Execute tool in the Deepadb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Deepadb MCP server in PolicyLayer and add a rule for adb_a11y_audit: 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_a11y_audit is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the adb_a11y_audit 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_a11y_audit. 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_a11y_audit 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.
Across the catalogue