Stop a running crawl job (API v2 POST /crawl/:id/stop).
AI agents invoke crawl_stop to trigger actions in Scrapegraph. 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 executes a command against an external service to stop/terminate a running process. While not destructive (the crawl data may persist), it is an Execute-category action because it triggers an external operation with side effects that depend on the supplied argument (the crawl job ID).
From the tool's definition Tool description states 'Stop a running crawl job', indicating it triggers an external operation (halting a web crawling process) via API endpoint POST /crawl/:id/stop.
Documented attack patterns abuse exactly the kind of access crawl_stop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Scrapegraph, and nothing reaches the server without passing your rules. This is the rule we recommend for crawl_stop:
{
"version": "1",
"default": "deny",
"tools": {
"crawl_stop": {
"limits": [
{
"counter": "crawl_stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}crawl_stop stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Stop a running crawl job (API v2 POST /crawl/:id/stop). It is categorised as a Execute tool in the Scrapegraph MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Scrapegraph MCP server in PolicyLayer and add a rule for crawl_stop: 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 Scrapegraph. Nothing to install.
crawl_stop 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 crawl_stop 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 crawl_stop. 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.
crawl_stop is provided by the Scrapegraph MCP server (ScrapeGraphAI/scrapegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Scrapegraph, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
17 Scrapegraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.