Compare CAMELS-style health scores across a group of FDIC-insured institutions. Three usage modes: - Explicit list: provide certs (up to 50) for a specific comparison set - State-wide scan: provide state to compare all active institutions in that state - Asset-based: provide asset_min/asset_max t...
Part of the Fdic server.
Free to start. No card required.
AI agents use fdic_compare_peer_health to create or modify resources in Fdic. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call fdic_compare_peer_health repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Fdic.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"fdic_compare_peer_health": {
"limits": [
{
"counter": "fdic_compare_peer_health_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Fdic policy for all 29 tools.
These attack patterns abuse exactly the kind of access fdic_compare_peer_health gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Compare CAMELS-style health scores across a group of FDIC-insured institutions. Three usage modes: - Explicit list: provide certs (up to 50) for a specific comparison set - State-wide scan: provide state to compare all active institutions in that state - Asset-based: provide asset_min/asset_max to compare institutions by size Optionally provide cert to highlight a subject institution's position in the ranking. Output: structuredContent includes {model, official_status, report_date, institutions, metrics, peer_context, proxy_summary, proxy, deprecations}. Institutions include proxy scores and name_source. When a subject cert is provided, metrics[] is the preferred subject-vs-peer array for new UI bindings and proxy_summary is a flattened subject proxy. peer_context.subject_percentiles is deprecated, remains for backward compatibility, and is targeted for removal only in a future coordinated major release. Auto-peer selection derives asset bands from report-date financials and broadens the cohort if fewer than 10 peers match. NOTE: Public off-site analytical proxy — not official supervisory ratings.. It is categorised as a Write tool in the Fdic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fdic MCP server in PolicyLayer and add a rule for fdic_compare_peer_health: 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 Fdic. Nothing to install.
fdic_compare_peer_health is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the fdic_compare_peer_health 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 fdic_compare_peer_health. 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.
fdic_compare_peer_health is provided by the Fdic MCP server (fdic-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 Fdic 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.