AI agents call factcheck.search to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query operation that retrieves and returns data from a fact-check corpus. It has no capability to modify, delete, execute code, or commit financial transactions. The tool is read-only and presents minimal risk even if misused by an AI agent, as it only exposes existing published fact-check data.
From the tool's definition Tool description states it 'Search[es] the global corpus of published fact-checks' and 'Returns matching claims' — purely informational retrieval with no modification or side effects.
Attacks that exploit this kind of access
Search the global corpus of published fact-checks (ClaimReview) by claim text. Returns matching claims with the claimant, claim date, and each review\. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for factcheck.search: 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. Nothing to install.
factcheck.search 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 factcheck.search 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 factcheck.search. 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.
factcheck.search is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →