Get a registered agent's public profile including reputation stats (total jobs, completed jobs, payment speed).
AI agents call get_agent_profile to retrieve information from Humanpages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
agent_id | string | Yes | The registered agent ID |
Parameters from the server's own tool schema.
This is a simple data retrieval operation that queries publicly available profile information. There is no capability to modify data, execute operations, delete information, or move money. The data returned is explicitly described as public profile information, making it a Read operation with minimal risk even if misused by an AI agent.
From the tool's definition Tool retrieves a public profile with reputation stats (total jobs, completed jobs, payment speed). The description uses 'Get' and indicates data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_agent_profile gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Humanpages, and nothing reaches the server without passing your rules. This is the rule we recommend for get_agent_profile:
{
"version": "1",
"default": "deny",
"tools": {
"get_agent_profile": {}
}
}get_agent_profile 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.
Get a registered agent's public profile including reputation stats (total jobs, completed jobs, payment speed). It is categorised as a Read tool in the Humanpages MCP Server, which means it retrieves data without modifying state.
get_agent_profile accepts 1 parameter: agent_id. Required: agent_id. The full parameter table on this page comes from the server's own tool schema.
Register the Humanpages MCP server in PolicyLayer and add a rule for get_agent_profile: 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 Humanpages. Nothing to install.
get_agent_profile 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_agent_profile 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_agent_profile. 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_agent_profile is provided by the Humanpages MCP server (humanpages). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Humanpages, 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.
40 Humanpages tools catalogued and risk-classified — across an index of 43,000+ MCP servers.