AI agents call dummy as a supporting operation in Blah workflows.
With no description and only the name 'dummy' to go on, there is no evidence of any meaningful side effect. 'Dummy' typically implies a placeholder or no-op. Confidence is very low due to lack of information; categorized as Other with low severity as the most defensible default.
From the tool's definition Tool name is 'dummy' and no description is provided, making it impossible to determine actual functionality.
Documented attack patterns abuse exactly the kind of access dummy 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 dummy:
{
"version": "1",
"default": "deny",
"tools": {
"dummy": {
"limits": [
{
"counter": "dummy_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}dummy gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
No description provided. It is categorised as a Other tool in the Blah MCP Server, which means it performs auxiliary operations.
Register the Blah MCP server in PolicyLayer and add a rule for dummy: 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.
dummy is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dummy 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 dummy. 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.
dummy 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.