read_crawl_data
AI agents call read_crawl_data to retrieve information from Screaming Frog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly implies data retrieval from existing crawl results. Given the server's purpose (SEO Spider operations including crawling and data export), this tool likely queries or retrieves previously stored crawl data. Without explicit evidence of side effects, destructive capability, or external operations, Read is the most appropriate category.
From the tool's definition Tool name 'read_crawl_data' explicitly indicates a read operation. The verb 'read' combined with 'crawl_data' (a noun describing stored results) suggests retrieval without modification.
Attacks that exploit this kind of access
read_crawl_data. It is categorised as a Read tool in the Screaming Frog MCP Server, which means it retrieves data without modifying state.
Register the Screaming Frog MCP server in PolicyLayer and add a rule for read_crawl_data: 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 Screaming Frog. Nothing to install.
read_crawl_data 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 read_crawl_data 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 read_crawl_data. 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.
read_crawl_data is provided by the Screaming Frog MCP server (marykovziridze/screaming-frog-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 →