Surface the weekly review digest — every metro that needs manual attention before the next newsletter cycle. Returns two buckets: 1. 🔴 Stale Progress (col AF=TRUE): a CRITICAL_NEGATIVE event hit a NOW/NEXT market since the last review. Published Tier (AE) may no longer be accurate. 2. 📋 Pending...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Cap Rate Signals server.
Free to start. No card required.
AI agents call get_weekly_review to retrieve information from Cap Rate Signals 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_weekly_review 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": {
"get_weekly_review": {}
}
}See the full Cap Rate Signals policy for all 14 tools.
These attack patterns abuse exactly the kind of access get_weekly_review 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.
Surface the weekly review digest — every metro that needs manual attention before the next newsletter cycle. Returns two buckets: 1. 🔴 Stale Progress (col AF=TRUE): a CRITICAL_NEGATIVE event hit a NOW/NEXT market since the last review. Published Tier (AE) may no longer be accurate. 2. 📋 Pending Tier Proposals (col AG non-empty): automated tier suggestions queued for human approval — call set_published_tier() to accept, or clear AG manually to reject. Trigger phrases: 'weekly review', 'what needs review this week', 'any stale flags?', 'pending tier changes', 'what needs my attention', 'run the weekly check', 'weekly sync', 'show me what moved'. It is categorised as a Read tool in the Cap Rate Signals MCP Server, which means it retrieves data without modifying state.
Register the Cap Rate Signals MCP server in PolicyLayer and add a rule for get_weekly_review: 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 Cap Rate Signals. Nothing to install.
get_weekly_review 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 get_weekly_review 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 get_weekly_review. 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.
get_weekly_review is provided by the Cap Rate Signals MCP server (capratesignals/cap-rate-signals). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Cap Rate Signals 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.