Return constructive improvement guidance for one area. Given an area identifier — an ISO-3166 alpha-3 country code, an EU NUTS-2 region code or a Dutch municipality CBS GM-code — returns that area's highest-impact improvement lever from the Cracks Index, together with Fynqo's approach to earlier,...
Part of the The Cracks Index server.
Free to start. No card required.
AI agents call improvement_guidance to retrieve information from The Cracks Index 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 improvement_guidance 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.
{
"version": "1",
"default": "deny",
"tools": {
"improvement_guidance": {}
}
}See the full The Cracks Index policy for all 15 tools.
These attack patterns abuse exactly the kind of access improvement_guidance gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Return constructive improvement guidance for one area. Given an area identifier — an ISO-3166 alpha-3 country code, an EU NUTS-2 region code or a Dutch municipality CBS GM-code — returns that area's highest-impact improvement lever from the Cracks Index, together with Fynqo's approach to earlier, joined-up coordination and a link to the public "claim your score" page where an organisation can request a deeper local report. Read-only, no personal data. The lever is framed as "the change most associated with improvement". It is general, aggregated guidance, not policy, medical, legal or financial advice, and carries no promise of a guaranteed score gain (sales-engine §3.4, §5).. It is categorised as a Read tool in the The Cracks Index MCP Server, which means it retrieves data without modifying state.
Register the The Cracks Index MCP server in PolicyLayer and add a rule for improvement_guidance: 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 The Cracks Index. Nothing to install.
improvement_guidance is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the improvement_guidance 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.
Set action: deny in the PolicyLayer policy for improvement_guidance. 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.
improvement_guidance is provided by the The Cracks Index MCP server (https://api.fynqo.app/mcp/cracks/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 The Cracks Index 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.