AI agents call fact_check to retrieve information from Jina AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Fact-checking is a read operation that retrieves validation information about statements without modifying any data, executing arbitrary code, or causing irreversible changes. It has minimal blast radius if misused—an AI could generate false claims or verify misinformation, but the tool itself only retrieves data. This aligns with the 'Read' category for tools that query or retrieve data with no side effects.
From the tool's definition Tool performs fact-checking via Jina AI services—a retrieval and validation operation that queries external fact-checking data.
Documented attack patterns abuse exactly the kind of access fact_check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jina AI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for fact_check:
{
"version": "1",
"default": "deny",
"tools": {
"fact_check": {}
}
}fact_check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fact-check a statement using Jina AI. It is categorised as a Read tool in the Jina AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jina AI MCP Server 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 Jina AI MCP Server. Nothing to install.
fact_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
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.
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.
fact_check is provided by the Jina AI MCP Server MCP server (joebuildsstuff/mcp-jina-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jina AI 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.
3 Jina AI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.