Retrieve a single person by their Humaans id. Employee-scoped custom field values are merged onto the person object as top-level keys named after the field (e.g. "Level": "IC5", "Cost Center": ["R&D"]). Native attributes win on name collisions.
AI agents call get_person to retrieve information from Humaans without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple lookup operation to fetch employee information by ID. It returns data without modifying, deleting, or executing any operations. While the returned data may include sensitive HR information (compensation, custom fields), the tool itself is a passive read operation with no blast radius for misuse beyond data exposure.
From the tool's definition Tool description states 'Retrieve a single person' and server is described as 'Read-only MCP server'. The verb 'Retrieve' and the read-only designation clearly indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Retrieve a single person by their Humaans id. Employee-scoped custom field values are merged onto the person object as top-level keys named after the field (e.g. "Level": "IC5", "Cost Center": ["R&D"]). Native attributes win on name collisions. It is categorised as a Read tool in the Humaans MCP Server, which means it retrieves data without modifying state.
Register the Humaans MCP server in PolicyLayer and add a rule for get_person: 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 Humaans. Nothing to install.
get_person 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 get_person 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 get_person. 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.
get_person is provided by the Humaans MCP server (ptorsten/humaans-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 →