Low Risk

recommend_tools

recommend_tools

How to control recommend_tools ↓

What recommend_tools does on Openstudio

AI agents call recommend_tools as a supporting operation in Openstudio workflows.

Low Risk

Why recommend_tools needs a policy

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:

How to control recommend_tools

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:

policy.json
{
  "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.

  1. Create a free account and register Openstudio — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
SET A RULE FOR THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about recommend_tools

What does the recommend_tools tool do? +

recommend_tools. It is categorised as a Other tool in the Openstudio MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on recommend_tools? +

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.

What risk level is recommend_tools? +

recommend_tools is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit recommend_tools? +

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.

How do I block recommend_tools completely? +

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.

What MCP server provides recommend_tools? +

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.

Enforce policy on every Openstudio tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.