Get recommended validation path based on what you need to validate and what resources you have. Returns a recommended path (1-5) with reasoning, matching templates, and a relevant playbook.
AI agents call select_validation_path to retrieve information from Agent Zone without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only fetches and returns recommendations based on input criteria. It does not create, modify, execute, or delete anything. It is a read-only advisory/query operation.
From the tool's definition 'Get recommended validation path' — returns recommendations, reasoning, matching templates, and a relevant playbook; purely retrieval/advisory with no side effects.
Attacks that exploit this kind of access
Get recommended validation path based on what you need to validate and what resources you have. Returns a recommended path (1-5) with reasoning, matching templates, and a relevant playbook. It is categorised as a Read tool in the Agent Zone MCP Server, which means it retrieves data without modifying state.
Register the Agent Zone MCP server in PolicyLayer and add a rule for select_validation_path: 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 Agent Zone. Nothing to install.
select_validation_path 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 select_validation_path 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 select_validation_path. 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.
select_validation_path is provided by the Agent Zone MCP server (statherm/agent-zone-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 →