AI agents call add as a supporting operation in Blah workflows.
With only the name 'add' and no description, the action could be anything (add a record, add numbers, add a server, etc.). Without more context, it cannot be reliably classified beyond 'Other'. Confidence is very low due to the absence of a description.
From the tool's definition Tool name is 'add' and description is empty or uninformative — no evidence of what this tool does.
Documented attack patterns abuse exactly the kind of access add 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 add:
{
"version": "1",
"default": "deny",
"tools": {
"add": {
"limits": [
{
"counter": "add_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}add gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
add. 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 add: 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.
add 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 add 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 add. 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.
add 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.