AI agents call getToken to retrieve information from Blah without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name implies retrieving or reading a token without side effects. However, the empty description significantly reduces confidence. If this tool generates a new token rather than retrieving an existing one, it could be Write. If it grants elevated privileges, severity could increase. Classification assumes read-only token retrieval based on nomenclature alone.
From the tool's definition Tool name 'getToken' suggests retrieval of an authentication token. Description is empty, limiting certainty.
Documented attack patterns abuse exactly the kind of access getToken gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Blah, and nothing reaches the server without passing your rules. This is the rule we recommend for getToken:
{
"version": "1",
"default": "deny",
"tools": {
"getToken": {}
}
}getToken is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
getToken. It is categorised as a Read tool in the Blah MCP Server, which means it retrieves data without modifying state.
Register the Blah MCP server in PolicyLayer and add a rule for getToken: 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 Blah. Nothing to install.
getToken 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 getToken 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 getToken. 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.
getToken is provided by the Blah MCP server (thomasdavis/blah). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Blah, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Blah tools catalogued and risk-classified — across an index of 43,000+ MCP servers.