Rank all areas by a single chosen indicator. Returns every area's value for one indicator, ordered best-first by the direction-corrected normalized_score (a higher normalised score always means fewer cracks on that indicator). The raw value and unit are included so the figure can be quoted direct...
Part of the The Cracks Index server.
Free to start. No card required.
AI agents call indicator_ranking 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 indicator_ranking 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": {
"indicator_ranking": {}
}
}See the full The Cracks Index policy for all 15 tools.
These attack patterns abuse exactly the kind of access indicator_ranking 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.
Rank all areas by a single chosen indicator. Returns every area's value for one indicator, ordered best-first by the direction-corrected normalized_score (a higher normalised score always means fewer cracks on that indicator). The raw value and unit are included so the figure can be quoted directly. Read-only, area-level aggregates only, no personal data.. 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 indicator_ranking: 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.
indicator_ranking 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 indicator_ranking 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 indicator_ranking. 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.
indicator_ranking 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.