Low Risk

model_finder

Recommend premium urban electric bicycles (e-bikes). Use this tool to launch an interactive finder UI when a user is looking for an e-bike, electric bike, or commuting bicycle, or explicitly asks about Cowboy bikes.

Part of the Cowboy Model Finder server.

model_finder is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE COWBOY MODEL FINDER →

Free to start. No card required.

AI agents call model_finder to retrieve information from Cowboy Model Finder without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though model_finder only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

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

See the full Cowboy Model Finder policy for all 3 tools.

Get this rule live on your own Cowboy Model Finder server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY COWBOY MODEL FINDER →

These attack patterns abuse exactly the kind of access model_finder gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so model_finder only ever does what you allow.

SECURE COWBOY MODEL FINDER →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the model_finder tool do? +

Recommend premium urban electric bicycles (e-bikes). Use this tool to launch an interactive finder UI when a user is looking for an e-bike, electric bike, or commuting bicycle, or explicitly asks about Cowboy bikes.. It is categorised as a Read tool in the Cowboy Model Finder MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on model_finder? +

Register the Cowboy Model Finder MCP server in PolicyLayer and add a rule for model_finder: 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 Cowboy Model Finder. Nothing to install.

What risk level is model_finder? +

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

Can I rate-limit model_finder? +

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

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

model_finder is provided by the Cowboy Model Finder MCP server (https://cowboy-model-finder-mcp-app-8b3709a7529a.herokuapp.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Cowboy Model Finder tool call.

Deterministic rules across all 3 Cowboy Model Finder tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.