AI agents call validate to retrieve information from Robot Md without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The validate tool performs validation checks and returns a boolean status with error details. It reads and assesses the ROBOT.md manifest without creating, modifying, deleting, or executing any code. This is a pure inspection/query operation with no side effects, placing it firmly in the Read category with low severity and high confidence.
From the tool's definition Tool description states it 'Validate[s] the served ROBOT.md against the v1 JSON schema' and 'Returns { ok: boolean, errors: [...] }'. No modification of data occurs; it only validates and reports results.
Attacks that exploit this kind of access
Validate the served ROBOT.md against the v1 JSON schema and body requirements. Returns { ok: boolean, errors: [...] }. Run this after any edit to the manifest, or when the operator asks. It is categorised as a Read tool in the Robot Md MCP Server, which means it retrieves data without modifying state.
Register the Robot Md MCP server in PolicyLayer and add a rule for validate: 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 Robot Md. Nothing to install.
validate 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 validate 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 validate. 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.
validate is provided by the Robot Md MCP server (robotregistryfoundation/robot-md-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 →