Update a specific group in Requestly.
AI agents use update_group to create or update resources in Requestly MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Requestly MCP Server environment.
The tool modifies an existing resource (a group) but does not delete or destroy it. Updating is a reversible Write operation. Severity is medium because misuse could alter configurations or organizational settings in Requestly, but the impact is limited to a single group and can be corrected by further updates.
From the tool's definition Tool name is 'update_group' with description 'Update a specific group in Requestly.' The verb 'update' indicates modification of existing data. This is a reversible operation—groups can be updated again or restored.
Attacks that exploit this kind of access
Update a specific group in Requestly. It is categorised as a Write tool in the Requestly MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Requestly MCP Server MCP server in PolicyLayer and add a rule for update_group: 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 Requestly MCP Server. Nothing to install.
update_group 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 update_group 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 update_group. 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.
update_group is provided by the Requestly MCP Server MCP server (requestly/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 →