Modify a Velociraptor hunt state.
AI agents use modify_hunt to create or update resources in Megaraptor MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Megaraptor MCP environment.
An AI agent can call modify_hunt faster than any human can review — one bad instruction and it creates or modifies resources in Megaraptor MCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Modify a Velociraptor hunt state. It is categorised as a Write tool in the Megaraptor MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Megaraptor MCP server in PolicyLayer and add a rule for modify_hunt: 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 Megaraptor MCP. Nothing to install.
modify_hunt is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the modify_hunt 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 modify_hunt. 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.
modify_hunt is provided by the Megaraptor MCP server (wagonbomb/megaraptor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.