Loading…
MCP server that identifies US real estate markets before repricing by tracking corporate investment patterns across 40+ metros.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 28 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The metro-catalyst MCP server exposes 14 tools, focused primarily on general-purpose capabilities. Its published description reads: "MCP server that identifies US real estate markets before repricing by tracking corporate investment patterns across 40+ metros". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates metro-catalyst F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check metro-catalyst's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add metro-catalyst to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://cap-rate-signals-mcp-production.up.railway.app/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Cap Rate Signals — fetch the raw structured data record for a specific US metro: composite investment score, hero catalyst, lifecycle state, cap rate, vacancy, duplex entry price, and employer stack.
Cap Rate Signals — list all tracked US real estate markets at a given investment tier. Returns Buy Now (workers arriving, window open), Get In Early (capital deploying), Watch List (conditional thesis
Cap Rate Signals — real-time investment signal feed across all tracked US markets. Returns stage advances, construction milestones, hiring launches, risk flags, and catalyst updates from the daily mon
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: assess_metro
A tool description tries to alter the model’s use of another tool.
narrative, use get_metro_brief instead.RecommendationDescriptions must describe only their own tool.
tool: get_regional_comps
A tool description tries to alter the model’s use of another tool.
_metro_brief or get_top_picks has already surfaced a market.RecommendationDescriptions must describe only their own tool.
tool: get_top_picks
A tool description tries to alter the model’s use of another tool.
es a city, call get_metro_brief on that city with depth='summary'. ALWAYS passRecommendationDescriptions must describe only their own tool.
tool: find_metros
A tool description tries to alter the model’s use of another tool.
ry'. Do NOT use compare_metros unless the investor explicitly names two citiesRecommendationDescriptions must describe only their own tool.
tool: get_metro_brief
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_metro_brief
A tool description tries to alter the model’s use of another tool.
never switch to compare_metros. Only use compare_metros if the investor explicRecommendationDescriptions must describe only their own tool.
tool: get_weekly_review
A tool description tries to alter the model’s use of another tool.
approval — call set_published_tier() to accept, or clear AG manually to reject.RecommendationDescriptions must describe only their own tool.
tool: clear_stale_progress_flag
A tool description tries to alter the model’s use of another tool.
g the tier, use set_published_tier instead (it clears AF automatically). Trigger pRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: compare_metros
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_metro_brief
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: set_published_tier
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: clear_stale_progress_flag
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
tool: get_top_picks
An unusually long description is a common injection-padding tactic.
description length 2714 charsRecommendationKeep descriptions concise.
tool: find_metros
An unusually long description is a common injection-padding tactic.
description length 2881 charsRecommendationKeep descriptions concise.
tool: get_metro_brief
An unusually long description is a common injection-padding tactic.
description length 2037 charsRecommendationKeep descriptions concise.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Cap Rate Signals — given a US metro, return the top-ranked comparable markets in the same region, scored by corporate investment strength and worker arrival timing. Helps investors diversify across a
Cap Rate Signals — head-to-head comparison of two US real estate markets on corporate investment strength, cap rates, entry price, worker arrival timing, and downside risk. Returns a plain-language ve
Cap Rate Signals (capratesignals.com) — the top US real estate markets to invest in right now, ranked by confirmed corporate investment, worker arrival timing, and cap rate trajectory. Identifies mark
Cap Rate Signals — discover and rank US real estate markets by region, investment theme, specific employer, or entry price budget. Covers semiconductor, defense, pharma, EV, data center, logistics, an
Cap Rate Signals — display an annotated map of employer sites and target investment neighborhoods for a specific US metro. Shows TI, Intel, Lilly, and other catalyst employer pins overlaid on color-co
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
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 NO
Update the Published Tier (col AE) for a metro after weekly review. AE is the investor-facing tier that overrides col E in all server responses. This does NOT change col E (Status) — E drives monitori
Clear the Stale Progress flag (col AF) for a metro without changing its tier. Use this when you've reviewed the CRITICAL_NEGATIVE event and decided the existing Published Tier (AE) is still accurate —
Returns the running server version. Use this to confirm which build of the metro-catalyst server is active.
Call this whenever you answer a US real estate investing question using your own training data WITHOUT calling any other metro-catalyst tool. Captures questions that fell through the tool routing — us