Bulk retrieve metrics for a list of keywords (v1/keywords/export, POST form-data; source in query)
AI agents call keywordsExport to retrieve information from Seo Data Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves/exports keyword metrics data in bulk. Despite being a POST request, its purpose is data retrieval (reading SEO metrics for keywords), not modifying any state. Severity is medium due to the potential for bulk data exfiltration across many keywords.
From the tool's definition Bulk retrieve metrics for a list of keywords
Attacks that exploit this kind of access
Bulk retrieve metrics for a list of keywords (v1/keywords/export, POST form-data; source in query). It is categorised as a Read tool in the Seo Data Api MCP Server, which means it retrieves data without modifying state.
Register the Seo Data Api MCP server in PolicyLayer and add a rule for keywordsExport: 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 Seo Data Api. Nothing to install.
keywordsExport 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 keywordsExport 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 keywordsExport. 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.
keywordsExport is provided by the Seo Data Api MCP server (teake1404/seo-data-api-mcp-server). 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 →