Submit a URL for forced re-crawl. Daily quota ~10 per host (depends on SQI).
AI agents invoke recrawl_url to trigger actions in SergeyKrin9/mcp Servers. 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.
This tool triggers an external operation (forced re-crawl by Yandex.Webmaster) on a specified URL. It doesn't merely read data or write/modify content — it actively initiates a crawl action on an external system. Misuse could exhaust the daily quota (~10/host) or trigger unwanted re-indexing, making it Execute-level with medium severity.
From the tool's definition Submit a URL for forced re-crawl. Daily quota ~10 per host
Attacks that exploit this kind of access
Submit a URL for forced re-crawl. Daily quota ~10 per host (depends on SQI). It is categorised as a Execute tool in the SergeyKrin9/mcp Servers MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SergeyKrin9/mcp Servers MCP server in PolicyLayer and add a rule for recrawl_url: 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 SergeyKrin9/mcp Servers. Nothing to install.
recrawl_url 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 recrawl_url 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 recrawl_url. 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.
recrawl_url is provided by the SergeyKrin9/mcp Servers MCP server (sergeykrin9/mcp-servers). 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 →