AI agents call inspect_request to retrieve information from Hookray without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads and returns information about previously captured webhook requests. It performs query/inspection operations without creating, modifying, deleting, or executing anything. The low severity reflects minimal blast radius if misused by an agent — at worst, it reveals data already captured in the webhook inbox.
From the tool's definition Tool description states 'Inspect the full headers, body, query params, and metadata for a captured request' — this is a retrieval and inspection operation with no modification or side effects.
Attacks that exploit this kind of access
Inspect the full headers, body, query params, and metadata for a captured request. It is categorised as a Read tool in the Hookray MCP Server, which means it retrieves data without modifying state.
Register the Hookray MCP server in PolicyLayer and add a rule for inspect_request: 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 Hookray. Nothing to install.
inspect_request 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 inspect_request 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 inspect_request. 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.
inspect_request is provided by the Hookray MCP server (shotatanikawa/hookray-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 →