Low Risk

start_search

Start a paginated file search. Returns searchId for retrieving results. Use for large directories.

How to control start_search ↓

What start_search does on OODA Computer Control

AI agents call start_search to retrieve information from OODA Computer Control without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why start_search needs a policy

This tool initiates a file search operation and returns an identifier for paginated results. It only reads/queries the filesystem with no side effects, modifications, or destructive actions.

From the tool's definition Start a paginated file search. Returns searchId for retrieving results.

Documented attack patterns abuse exactly the kind of access start_search gives an agent:

How to control start_search

PolicyLayer is an MCP gateway — it sits between your AI agents and OODA Computer Control, and nothing reaches the server without passing your rules. This is the rule we recommend for start_search:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_search": {}
  }
}

start_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register OODA Computer Control — 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.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about start_search

What does the start_search tool do? +

Start a paginated file search. Returns searchId for retrieving results. Use for large directories. It is categorised as a Read tool in the OODA Computer Control MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on start_search? +

Register the OODA Computer Control MCP server in PolicyLayer and add a rule for start_search: 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 OODA Computer Control. Nothing to install.

What risk level is start_search? +

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

Can I rate-limit start_search? +

Yes. Add a rate_limit block to the start_search 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 start_search completely? +

Set action: deny in the PolicyLayer policy for start_search. 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 start_search? +

start_search is provided by the OODA Computer Control MCP server (mnehmos/mnehmos.ooda.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OODA Computer Control tool call.

Start from OODA Computer Control, 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.

99 OODA Computer Control 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.