Run a color contrast audit on a URL. Returns elements failing WCAG contrast ratios with severity and details. Scans one page per call. Free plans include 3 scans per day; Pro is unlimited.
AI agents call scan_contrast to retrieve information from OverlayQA MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only diagnostic tool that audits web pages for accessibility issues. It queries a URL, inspects the page's color contrast properties, and returns structured findings. No data is created, modified, or deleted, and no code is executed. The tool has minimal blast radius—misuse would at worst result in wasted scan quota or exposure of audit results about publicly accessible pages.
From the tool's definition Tool performs a scan and returns audit results ("Returns elements failing WCAG contrast ratios with severity and details"). It analyzes a URL but does not modify, execute code, delete data, or move funds.
Attacks that exploit this kind of access
Run a color contrast audit on a URL. Returns elements failing WCAG contrast ratios with severity and details. Scans one page per call. Free plans include 3 scans per day; Pro is unlimited. It is categorised as a Read tool in the OverlayQA MCP MCP Server, which means it retrieves data without modifying state.
Register the OverlayQA MCP server in PolicyLayer and add a rule for scan_contrast: 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 OverlayQA MCP. Nothing to install.
scan_contrast 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 scan_contrast 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 scan_contrast. 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.
scan_contrast is provided by the OverlayQA MCP server (overlayqa/mcp). 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 →