Low Risk

get_ej_county_summary

Get EJ indicators for census block groups in a county. Returns EJScreen environmental justice data for block groups within the specified county, sorted by highest overall environmental burden. Includes environmental indicators, demographic data, and EJ indexes. Args: state: Two-letter US state ab...

Part of the EPA EJScreen server.

get_ej_county_summary 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 EPA EJSCREEN →

Free to start. No card required.

AI agents call get_ej_county_summary to retrieve information from EPA EJScreen 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_ej_county_summary 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_ej_county_summary": {}
  }
}

See the full EPA EJScreen policy for all 5 tools.

Get this rule live on your own EPA EJScreen server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY EPA EJSCREEN →

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

SECURE EPA EJSCREEN →

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

What does the get_ej_county_summary tool do? +

Get EJ indicators for census block groups in a county. Returns EJScreen environmental justice data for block groups within the specified county, sorted by highest overall environmental burden. Includes environmental indicators, demographic data, and EJ indexes. Args: state: Two-letter US state abbreviation (e.g. 'WA', 'CA'). county_fips: County FIPS code, either 5-digit full (e.g. '53033') or 3-digit county portion (e.g. '033'). If 3 digits, state FIPS is prepended automatically. limit: Maximum number of block groups to return (default 50, max 500).. It is categorised as a Read tool in the EPA EJScreen MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_ej_county_summary? +

Register the EPA EJScreen MCP server in PolicyLayer and add a rule for get_ej_county_summary: 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 EPA EJScreen. Nothing to install.

What risk level is get_ej_county_summary? +

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

Can I rate-limit get_ej_county_summary? +

Yes. Add a rate_limit block to the get_ej_county_summary 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_ej_county_summary completely? +

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

get_ej_county_summary is provided by the EPA EJScreen MCP server (https://mcp.olyport.com/ejscreen/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every EPA EJScreen tool call.

Deterministic rules across all 5 EPA EJScreen 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.