AI agents invoke retry_webhook to trigger actions in GoHighLevel 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.
Retrying a webhook delivery triggers an external HTTP request/operation to a remote endpoint. This is an execution action that causes side effects in external systems depending on the webhook's payload and target. It is not merely reading data, nor does it directly delete data or move money, but it does trigger an external operation whose effects depend on the webhook arguments/content.
From the tool's definition Retry a failed webhook delivery
Documented attack patterns abuse exactly the kind of access retry_webhook gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GoHighLevel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for retry_webhook:
{
"version": "1",
"default": "deny",
"tools": {
"retry_webhook": {
"limits": [
{
"counter": "retry_webhook_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} retry_webhook stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retry a failed webhook delivery. It is categorised as a Execute tool in the GoHighLevel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GoHighLevel MCP Server MCP server in PolicyLayer and add a rule for retry_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 GoHighLevel MCP Server. Nothing to install.
retry_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 retry_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 retry_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.
retry_webhook is provided by the GoHighLevel MCP Server MCP server (busybee3333/go-high-level-mcp-2026-complete). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 566 GoHighLevel MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
566 GoHighLevel MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.