replay_webhook_delivery
AI agents invoke replay_webhook_delivery to trigger actions in Thesma 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.
The name implies re-executing or re-sending a webhook event, which is an external operation that triggers side effects on downstream systems. This falls under Execute rather than Write because it re-fires an external operation. Severity is high because replaying webhooks could trigger duplicate processing, financial actions, or data mutations in external systems.
From the tool's definition Tool name 'replay_webhook_delivery' suggests re-triggering a past webhook delivery; description is empty and uninformative.
Attacks that exploit this kind of access
replay_webhook_delivery. It is categorised as a Execute tool in the Thesma MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Thesma MCP Server MCP server in PolicyLayer and add a rule for replay_webhook_delivery: 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 Thesma MCP Server. Nothing to install.
replay_webhook_delivery 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 replay_webhook_delivery 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 replay_webhook_delivery. 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.
replay_webhook_delivery is provided by the Thesma MCP Server MCP server (thesma-dev/thesma-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 →