score_humanity
AI agents call score_humanity to retrieve information from HumanizeMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
With an empty description, confidence is reduced. Based on the name alone, this appears to be an analytical/scoring function that reads text and returns a metric, classifying it as Read. The sibling tools (humanize, detect_tells, humanize_and_verify) suggest the server is focused on analyzing and rewriting text rather than executing arbitrary code or destructive operations.
From the tool's definition Tool name 'score_humanity' suggests it retrieves or measures a humanity score, without description provided. No indication of modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
score_humanity. It is categorised as a Read tool in the HumanizeMCP MCP Server, which means it retrieves data without modifying state.
Register the Humanize MCP server in PolicyLayer and add a rule for score_humanity: 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 HumanizeMCP. Nothing to install.
score_humanity 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 score_humanity 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 score_humanity. 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.
score_humanity is provided by the Humanize MCP server (kitfoxs/humanize-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 →