Trigger an immediate collection cycle to populate the vector store. Fetches all intelligence sources and stores them. Optional: sources (comma-separated domain groups like
AI agents invoke intel_collect to trigger actions in Threat Intelligence MCP Server. 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 defined operation that triggers background processes to fetch and aggregate data from external threat intelligence sources (Feodo Tracker, URLhaus, CISA KEV, ThreatFox, VirusTotal, AbuseIPDB, Shodan). While the operation itself is not destructive or irreversible, it performs computational work and external system interactions whose effects depend on execution parameters.
From the tool's definition Tool description states 'Trigger an immediate collection cycle' and 'Fetches all intelligence sources and stores them', indicating execution of a data collection process with external side effects (populating a vector store, querying multiple threat…
Documented attack patterns abuse exactly the kind of access intel_collect gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Threat Intelligence MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for intel_collect:
{
"version": "1",
"default": "deny",
"tools": {
"intel_collect": {
"limits": [
{
"counter": "intel_collect_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}intel_collect 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.
Trigger an immediate collection cycle to populate the vector store. Fetches all intelligence sources and stores them. Optional: sources (comma-separated domain groups like. It is categorised as a Execute tool in the Threat Intelligence MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Threat Intelligence MCP Server MCP server in PolicyLayer and add a rule for intel_collect: 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 Threat Intelligence MCP Server. Nothing to install.
intel_collect 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 intel_collect 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 intel_collect. 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.
intel_collect is provided by the Threat Intelligence MCP Server MCP server (marc-shade/world-intel-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Threat Intelligence MCP Server, 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.
113 Threat Intelligence MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.