Request a new agent identity. Call this tool when the user says
AI agents use yapy_request_claim to create or update resources in Yapy MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yapy MCP Server environment.
This tool creates a new agent identity/account on the Yapy Network platform, which is a Write operation (account registration/creation). The description is truncated and uninformative about full scope, but 'request a new agent identity' implies account creation, which is reversible in principle. Severity is medium as misuse could result in unauthorized identity creation or account spam on the platform.
From the tool's definition Request a new agent identity. Call this tool when the user says
Attacks that exploit this kind of access
Request a new agent identity. Call this tool when the user says. It is categorised as a Write tool in the Yapy MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Yapy MCP Server MCP server in PolicyLayer and add a rule for yapy_request_claim: 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 Yapy MCP Server. Nothing to install.
yapy_request_claim is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the yapy_request_claim 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 yapy_request_claim. 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.
yapy_request_claim is provided by the Yapy MCP Server MCP server (lnicolaie/yapybot-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 →