AI agents call verify_hash to retrieve information from Unfakable without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only lookup of hash verification results. It queries an external verification service (Unfakable) to check if a SHA-256 fingerprint exists in a known database, similar to checking a list. The operation has no side effects, produces no state changes, and returns only informational results about file authenticity status.
From the tool's definition Tool name 'verify_hash' and description 'Look up a known SHA-256 fingerprint directly against Unfakable' indicate a query/lookup operation that retrieves verification data without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Look up a known SHA-256 fingerprint directly against Unfakable. It is categorised as a Read tool in the Unfakable MCP Server, which means it retrieves data without modifying state.
Register the Unfakable MCP server in PolicyLayer and add a rule for verify_hash: 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 Unfakable. Nothing to install.
verify_hash 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 verify_hash 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 verify_hash. 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.
verify_hash is provided by the Unfakable MCP server (unfakable/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 →