Audit a Semiotic chart configuration against the Chartability (POUR-CAF) accessibility framework — Perceivable, Operable, Understandable, Robust, Compromising, Assistive, Flexible. Statically grades the config (no DOM/AT): credits the built-ins every HOC ships (keyboard nav, focus ring, skip link...
AI agents call auditAccessibility to retrieve information from Semiotic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
auditAccessibility is a read-only diagnostic tool that analyzes and reports on chart accessibility compliance without modifying, executing, or destroying any data. It retrieves information about configuration issues and provides feedback for human decision-making. No irreversible changes, code execution, or external operations are triggered by this tool.
From the tool's definition The tool performs static analysis and auditing of chart configurations against accessibility standards. The description states it 'Statically grades the config', 'credits the built-ins', 'flags author-actionable gaps', and 'routes everything that needs real…
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Audit a Semiotic chart configuration against the Chartability (POUR-CAF) accessibility framework — Perceivable, Operable, Understandable, Robust, Compromising, Assistive, Flexible. Statically grades the config (no DOM/AT): credits the built-ins every HOC ships (keyboard nav, focus ring, skip link, screen-reader data table, reduced-motion + forced-colors, shareable state), flags author-actionable gaps (missing title/description/summary, low contrast, small text, color-only encoding, undescribed trends, data density), and routes everything that needs real assistive-technology testing to a. It is categorised as a Read tool in the Semiotic MCP Server, which means it retrieves data without modifying state.
Register the Semiotic MCP server in PolicyLayer and add a rule for auditAccessibility: 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 Semiotic. Nothing to install.
auditAccessibility 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 auditAccessibility 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 auditAccessibility. 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.
auditAccessibility is provided by the Semiotic MCP server (semiotic). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →