kya_reputation_model · UMBRAXON/kya Hub MCP: Risk & Policy

WHAT IT DOES

What kya_reputation_model does on UMBRAXON/kya Hub

AI agents call kya_reputation_model to retrieve information from UMBRAXON/kya Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

WHY IT NEEDS A POLICY

Why kya_reputation_model needs a policy

This tool retrieves reputation model data via a GET endpoint with no capability to modify, execute, or delete. The read-only nature and fetch-based operation make this a Read category tool with low severity, as it only queries and returns data without side effects.

From the tool's definition Tool description indicates 'GET /api/protocol/reputation-model', which is a read-only HTTP GET request. Server description emphasizes it is a 'Read-only MCP server' that 'Exposes tools to fetch' reputation data and other metadata.

Attacks that exploit this kind of access

Questions about kya_reputation_model

What does the kya_reputation_model tool do? +

GET /api/protocol/reputation-model. It is categorised as a Read tool in the UMBRAXON/kya Hub MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on kya_reputation_model? +

Register the UMBRAXON/kya Hub MCP server in PolicyLayer and add a rule for kya_reputation_model: 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 UMBRAXON/kya Hub. Nothing to install.

What risk level is kya_reputation_model? +

kya_reputation_model is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit kya_reputation_model? +

Yes. Add a rate_limit block to the kya_reputation_model 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.

How do I block kya_reputation_model completely? +

Set action: deny in the PolicyLayer policy for kya_reputation_model. 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.

What MCP server provides kya_reputation_model? +

kya_reputation_model is provided by the UMBRAXON/kya Hub MCP server (umbraxon/kya-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.