AI agents invoke cancelCrawl to trigger actions in MCP-RSS-Crawler. 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.
Cancelling a running crawl job is an operational action that terminates an in-progress execution. It doesn't merely read data, but actively stops/interrupts an ongoing process. While it could be seen as somewhat reversible (you can start a new crawl), it does affect external system state by terminating a job. Execute is the most appropriate category as it triggers an external operation (stopping a running job).
From the tool's definition Cancel an asynchronous crawl job
Documented attack patterns abuse exactly the kind of access cancelCrawl gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-RSS-Crawler, and nothing reaches the server without passing your rules. This is the rule we recommend for cancelCrawl:
{
"version": "1",
"default": "deny",
"tools": {
"cancelCrawl": {
"limits": [
{
"counter": "cancelcrawl_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cancelCrawl 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.
Cancel an asynchronous crawl job. It is categorised as a Execute tool in the MCP-RSS-Crawler MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP-RSS-Crawler MCP server in PolicyLayer and add a rule for cancelCrawl: 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 MCP-RSS-Crawler. Nothing to install.
cancelCrawl 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 cancelCrawl 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 cancelCrawl. 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.
cancelCrawl is provided by the MCP-RSS-Crawler MCP server (mshk/mcp-rss-crawler). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-RSS-Crawler, 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.
18 MCP-RSS-Crawler tools catalogued and risk-classified — across an index of 43,000+ MCP servers.