Get an API token by ID. The secret token value is NOT returned here — only the metadata (name, last 4 digits, resources).
AI agents call get-api-token to retrieve information from Mcp Mailtrap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that retrieves metadata about an API token without exposing the actual secret. It has no side effects, does not modify data, and does not execute code or perform destructive actions. The blast radius is minimal since only metadata is accessible and the actual secret is explicitly not returned.
From the tool's definition Tool description states 'Get an API token by ID' and 'only the metadata (name, last 4 digits, resources)' are returned. No secret value is exposed, and the operation is a simple retrieval of non-sensitive metadata.
Attacks that exploit this kind of access
Get an API token by ID. The secret token value is NOT returned here — only the metadata (name, last 4 digits, resources). It is categorised as a Read tool in the Mcp Mailtrap MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mailtrap MCP server in PolicyLayer and add a rule for get-api-token: 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 Mcp Mailtrap. Nothing to install.
get-api-token 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 get-api-token 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 get-api-token. 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.
get-api-token is provided by the Mcp Mailtrap MCP server (mcp-mailtrap). 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 →