postmark_list_bounces
AI agents call postmark_list_bounces to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries bounce data from an email service with no modification capability or side effects. It falls squarely into the Read category. The blast radius is minimal since listing bounces cannot cause damage—it merely exposes bounce event information. Severity is low.
From the tool's definition Tool name 'postmark_list_bounces' indicates a list operation that retrieves bounce records from Postmark email service. The 'list' prefix and 'bounces' noun identify this as a query/retrieval function. No description provided, but naming convention is clear.
Attacks that exploit this kind of access
postmark_list_bounces. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for postmark_list_bounces: 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 Integrations MCP. Nothing to install.
postmark_list_bounces is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the postmark_list_bounces 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 postmark_list_bounces. 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.
postmark_list_bounces is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →