resend_webhook
AI agents invoke resend_webhook to trigger actions in Terra Config MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Resending a webhook typically triggers an external HTTP request/callback to a configured endpoint, which is an external operation (Execute category). However, with no description available, confidence is low. It is not clearly destructive, financial, or a simple read/write, so Execute is the most likely category given the name implies firing an outbound event.
From the tool's definition Tool name 'resend_webhook' suggests triggering an external HTTP operation (webhook delivery), but the description is empty and uninformative.
Attacks that exploit this kind of access
resend_webhook. It is categorised as a Execute tool in the Terra Config MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Terra Config MCP Server MCP server in PolicyLayer and add a rule for resend_webhook: 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 Terra Config MCP Server. Nothing to install.
resend_webhook is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the resend_webhook 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 resend_webhook. 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.
resend_webhook is provided by the Terra Config MCP Server MCP server (tryterra/terramcp). 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 →