AI agents use set_request_base to create or update resources in Req — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Req environment.
This tool creates or modifies configuration data (the base URL) in a reversible manner. It does not retrieve data (Read), execute arbitrary code or commands (Execute), delete data (Destructive), or move money (Financial). The blast radius is low because misconfiguration of a base URL affects only the scope of future HTTP requests made by the user/agent, and can be easily corrected by calling the tool again.
From the tool's definition Tool description states it 'Sets the base URL used for future Request API calls' — this modifies configuration state that affects subsequent operations.
Attacks that exploit this kind of access
Sets the base URL used for future Request API calls. It is categorised as a Write tool in the Req MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Req MCP server in PolicyLayer and add a rule for set_request_base: 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 Req. Nothing to install.
set_request_base 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 set_request_base 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 set_request_base. 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.
set_request_base is provided by the Req MCP server (tarminarx/request-mcp-server). 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 →