GET /api/agent/{kya_id}/actions — optional limit (max 200) and offset.
AI agents call kya_agent_actions 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.
This tool retrieves agent action history with optional pagination. It performs a read-only query against the KYA-Hub API with no side effects, no code execution, and no data modification. The low severity reflects minimal blast radius—an agent misusing this tool can only access historical action records for a given agent ID, which are read-only.
From the tool's definition Tool name includes 'GET' and description explicitly states 'GET /api/agent/{kya_id}/actions' with optional pagination parameters (limit, offset). Server is described as 'Read-only MCP server' that 'fetches' data.
Attacks that exploit this kind of access
GET /api/agent/{kya_id}/actions — optional limit (max 200) and offset. It is categorised as a Read tool in the UMBRAXON/kya Hub MCP Server, which means it retrieves data without modifying state.
Register the UMBRAXON/kya Hub MCP server in PolicyLayer and add a rule for kya_agent_actions: 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.
kya_agent_actions 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 kya_agent_actions 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 kya_agent_actions. 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.
kya_agent_actions 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.
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 →