Low Risk

get_state_arrests

Get arrest data for a US state by offense category. Returns arrest statistics from the FBI Crime Data Explorer broken down by offense category for the specified state and year range. Args: state: Two-letter US state abbreviation (e.g. 'CA', 'TX', 'NY'). from_year: Start year for the data range (d...

Part of the FBI Crime Data server.

get_state_arrests 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 FBI CRIME DATA →

Free to start. No card required.

AI agents call get_state_arrests to retrieve information from FBI Crime Data 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 get_state_arrests 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": {
    "get_state_arrests": {}
  }
}

See the full FBI Crime Data policy for all 4 tools.

Get this rule live on your own FBI Crime Data server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY FBI CRIME DATA →

These attack patterns abuse exactly the kind of access get_state_arrests 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 get_state_arrests only ever does what you allow.

SECURE FBI CRIME DATA →

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

What does the get_state_arrests tool do? +

Get arrest data for a US state by offense category. Returns arrest statistics from the FBI Crime Data Explorer broken down by offense category for the specified state and year range. Args: state: Two-letter US state abbreviation (e.g. 'CA', 'TX', 'NY'). from_year: Start year for the data range (default 2015). to_year: End year for the data range (default 2023).. It is categorised as a Read tool in the FBI Crime Data MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_state_arrests? +

Register the FBI Crime Data MCP server in PolicyLayer and add a rule for get_state_arrests: 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 FBI Crime Data. Nothing to install.

What risk level is get_state_arrests? +

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

Can I rate-limit get_state_arrests? +

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

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

get_state_arrests is provided by the FBI Crime Data MCP server (https://mcp.olyport.com/fbi-crime/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every FBI Crime Data tool call.

Deterministic rules across all 4 FBI Crime Data 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.