AI agents call recommend_tools as a supporting operation in Openstudio workflows.
With an empty description, the tool's behavior is unknown. The name 'recommend_tools' suggests it may simply suggest or list available tools (a read-like operation), but without any description we cannot be certain. Given the context of sibling tools (energy simulation creation/modification), it likely just provides recommendations without side effects, placing it in 'Other' or 'Read'.
From the tool's definition Tool name is 'recommend_tools' with an empty description. No information about what it does.
Documented attack patterns abuse exactly the kind of access recommend_tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openstudio, and nothing reaches the server without passing your rules. This is the rule we recommend for recommend_tools:
{
"version": "1",
"default": "deny",
"tools": {
"recommend_tools": {
"limits": [
{
"counter": "recommend_tools_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
} recommend_tools gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
recommend_tools. It is categorised as a Other tool in the Openstudio MCP Server, which means it performs auxiliary operations.
Register the Openstudio MCP server in PolicyLayer and add a rule for recommend_tools: 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 Openstudio. Nothing to install.
recommend_tools 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 recommend_tools 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 recommend_tools. 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.
recommend_tools is provided by the Openstudio MCP server (natlabrockies/openstudio-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openstudio, 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.
146 Openstudio tools catalogued and risk-classified — across an index of 43,000+ MCP servers.