fact-check · MCP Document Processor MCP: Risk & Policy

WHAT IT DOES

What fact-check does on MCP Document Processor

AI agents invoke fact-check to trigger actions in MCP Document Processor. 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.

WHY IT NEEDS A POLICY

Why fact-check needs a policy

This tool triggers external operations (live web search via a separate MCP, get-web-search-summaries) and optionally writes output files. It spans Read, Execute, and Write categories. The most severe applicable is Execute because it orchestrates cross-MCP calls and triggers external network operations whose effects depend on the document/claims provided.

From the tool's definition CROSS-MCP tool: doc-processor extracts the claims, then CALLS the web-search MCP (get-web-search-summaries) to gather sources per claim, and optionally writes a cited PDF report

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fact-check Rate-limited

fact-check 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "fact-check": {
      "limits": [
        {
          "counter": "fact-check_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Document Processor, so you can run agents against it safely.

FAQ

Questions about fact-check

What does the fact-check tool do? +

Fact-check a document (or explicit claims) against the LIVE WEB. CROSS-MCP tool: doc-processor extracts the claims, then CALLS the web-search MCP (get-web-search-summaries) to gather sources per claim, and optionally writes a cited PDF report. It is categorised as a Execute tool in the MCP Document Processor MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on fact-check? +

Register the MCP Document Processor MCP server in PolicyLayer and add a rule for fact-check: 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 Document Processor. Nothing to install.

What risk level is fact-check? +

fact-check is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit fact-check? +

Yes. Add a rate_limit block to the fact-check 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.

How do I block fact-check completely? +

Set action: deny in the PolicyLayer policy for fact-check. 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.

What MCP server provides fact-check? +

fact-check is provided by the MCP Document Processor MCP server (leanzero-srl/leanzero-mcp-doc-processor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.