humanize
Rewrite text to sound human in a persona's voice. persona_id is required (call list_personas first). A blank value is rejected before any credit is spent. platform is an optional mode ("linkedin") that tightens the opening hook for that platform.
This record as markdown: /tools/com-givepersonhood-personhood/humanize.md
What humanize does on Personhood
AI agents call humanize to retrieve information from Personhood without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | |
context | object | — | |
platform | object | — | |
persona_id | string | Yes |
Parameters from the server's own tool schema.
Why humanize is rated Low
Even though humanize only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs humanize safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Personhood, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For humanize, this is the rule to start with:
humanize is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Personhood, apply this rule, and every humanize call is checked against it from then on.
Questions about humanize
Rewrite text to sound human in a persona's voice. persona_id is required (call list_personas first). A blank value is rejected before any credit is spent. platform is an optional mode ("linkedin") that tightens the opening hook for that platform. It is categorised as a Read tool in the Personhood MCP Server, which means it retrieves data without modifying state.
humanize accepts 4 parameters: text, context, platform, persona_id. Required: text, persona_id. The full parameter table on this page comes from the server's own tool schema.
Register the Personhood MCP server in PolicyLayer and add a rule for humanize: 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 Personhood. Nothing to install.
humanize 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 humanize 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 humanize. 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.
humanize is provided by the Personhood MCP server (https://api.givepersonhood.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Personhood, and thousands of servers like it.
This server
Across the catalogue