Cap Rate Signals — full investment brief on a specific US metro: conviction rating, catalyst stack, worker arrival timing, target neighborhoods, cap rates, entry price, and downside risks. The primary tool for any investor question about a named city. Triggers on phrasings like: 'should I invest ...
Risk signalsAccepts freeform code/query input (query)
Part of the Cap Rate Signals server.
Free to start. No card required.
AI agents call get_metro_brief 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_metro_brief 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_metro_brief": {}
}
}See the full Cap Rate Signals policy for all 14 tools.
These attack patterns abuse exactly the kind of access get_metro_brief 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.
Cap Rate Signals — full investment brief on a specific US metro: conviction rating, catalyst stack, worker arrival timing, target neighborhoods, cap rates, entry price, and downside risks. The primary tool for any investor question about a named city. Triggers on phrasings like: 'should I invest in Columbus?', 'is Indianapolis a good market?', 'what do you think about Sherman TX?', 'give me your take on Tulsa', 'is West Lafayette worth looking at?', 'what's your opinion on Knoxville?', 'tell me about St. Louis', 'explain the Columbus opportunity', 'walk me through Indianapolis', 'break down Sherman for me', 'give me the story on Knoxville', 'what's the deal with Tulsa?', 'what's happening in West Lafayette?', 'what's going on in Columbus?', 'how is Indianapolis doing?', 'how does Columbus look?', 'how is Sherman performing?', 'what's the market like in Knoxville?', 'what are conditions like in St. Louis?', 'I'm looking at Columbus', 'I'm thinking about Indianapolis', 'I'm considering Sherman TX', 'I have a deal in Bethlehem PA', 'I found a property in Tulsa', 'I'm underwriting a deal in West Lafayette', 'Columbus — yes or no?', 'Indianapolis — worth it?', 'quick take on Knoxville', 'is there opportunity in St. Louis?', 'is Sherman still good?', 'I heard Columbus is hot, is that true?', 'someone told me to look at Tulsa', 'I read about the Intel fab in Columbus', 'what does the Lilly investment mean for Indy?' Always start with depth='summary' (2-3 sentences). If the investor says 'go deeper', 'more detail', 'tell me more', or 'yes' — call again with depth='narrative' (full city breakdown). If the investor says 'full brief', 'everything', 'full picture', 'complete analysis', or 'LP brief' at ANY point — call immediately with depth='full' (complete LP-ready brief). Do not make the investor pass through narrative first if they asked for full. A bare 'yes' always means next depth on the same city — never switch to compare_metros. Only use compare_metros if the investor explicitly names two cities together.. 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_metro_brief: 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_metro_brief 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_metro_brief 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_metro_brief. 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_metro_brief 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.