AI agents use scf_create_webhook to create or update resources in Scf — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scf environment.
This tool creates a new webhook endpoint and generates a cryptographic secret, which is a reversible write operation (the webhook can be deleted or reconfigured). It is not destructive because webhook creation/modification is undoable.
From the tool's definition Tool description states 'Create a webhook endpoint' and 'write — admin role'. The verb 'create' and explicit 'write' label confirm data modification.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Create a webhook endpoint for evidence-inbox ingestion (write — admin role). Returns the plaintext HMAC signing secret exactly once — store it immediately; it cannot be retrieved later. It is categorised as a Write tool in the Scf MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scf MCP server in PolicyLayer and add a rule for scf_create_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 Scf. Nothing to install.
scf_create_webhook 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 scf_create_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 scf_create_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.
scf_create_webhook is provided by the Scf MCP server (mcp-server-scf). 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 →