AI agents use compute_extensions to create or update resources in Warrant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Warrant environment.
An AI agent can call compute_extensions faster than any human can review — one bad instruction and it creates or modifies resources in Warrant by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Compute acceptable arguments using Dung's semantics. It is categorised as a Write tool in the Warrant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Warrant MCP server in PolicyLayer and add a rule for compute_extensions: 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 Warrant. Nothing to install.
compute_extensions 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 compute_extensions 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 compute_extensions. 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.
compute_extensions is provided by the Warrant MCP server (jayden-chmod/warrant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
compute_extensions is one line of Warrant's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →