HORIZON SHIELD KIRA
Related Servers
Alternatives to HORIZON SHIELD KIRA
- AlicenseAqualityAmaintenanceReal Estate Listing - MCP server providing AI-powered tools and automation by MEOK AI Labs57 npm1MIT
- AlicenseAqualityAmaintenance| 地価トレンド予測 | 新宿区の5年後地価をAI予測。CAGR・投資シグナル付き | | 企業立地需要分析 | 名古屋市中区のオフィス・工場需要スコアを算出 | | ファミリー向け適性評価 | 横浜市西区の教育・安全・医療スコアを総合評価 | | ポートフォリオ最適化 | 東京・大阪・埼玉の3エリアに投資配分を最適化 | | What-If シナリオ分析 | 大阪市中央区で新駅開設シナリオを試算 | | 店舗出店適地評価 | 福岡市博多区の人流・商業施設・交通データで出店適性を判定 |3876 npm1AGPL 3.0
Related Servers
- FlicenseNot gradedqualityCmaintenanceCheck if a contractor's remodeling bid is fair — analyze a quote (fairness score + red flags), get 2026 cost estimates by city, and look up BLS trade labor rates.-
- AlicenseNot gradedqualityBmaintenanceEnables agents to turn customer conversations into provably correct remodeling quotes by extracting catalog-bounded line items with evidence and calculating prices deterministically.MIT
- AlicenseAqualityBmaintenanceProvides construction-supervision tools for small-to-medium building projects, including stage guidance, inspection checklists, progress tracking, next-stage recommendations, and quotation analysis. It enables local, standards-based MCP interaction over stdio without third-party MCP SDKs.5MIT
- AlicenseAqualityAmaintenanceAudits a live site for machine legibility (structured data, llms.txt, titles, headings), matches a trade to one of 14 website templates with demo links, and quotes real prices. Remote Streamable HTTP on MCP spec 2026-07-28, with an eval suite in the repo.2362 npmMIT
- AlicenseAqualityAmaintenanceEval-integrity statistics for AI benchmark claims — multiple-testing correction, power/MDE for model gaps, judge-bias and leaderboard-rank checks. Catches a benchmark number that won't survive a second look.9MIT
- FlicenseNot gradedqualityDmaintenanceProvides construction cost estimation tools using data from a public Google Sheet for items like concrete, framing, and electrical. It allows users to search items, filter by category, and calculate total project costs including labor and material expenses.-
TDQS
Scored across 14 tools
Several tools overlap in pricing/estimate checking: get_price_range, audit_estimate, preview_reverse_estimate, and verify_fair_price all deal with fair-price comparison, with audit_estimate and preview_reverse_estimate being very similar in purpose (checking a quoted amount against the range). However, descriptions contain clear usage guidance ('use X when...') that helps distinguish them, and the rest (categories, red flags, attestations, verification) are clearly distinct.
Naming is inconsistent: a mix of verbs like get_, list_, search_, audit_, check_, preview_, verify_, create_, suggest_ without a uniform pattern (e.g., 'check_red_flags' vs. 'audit_estimate' vs. 'verify_fair_price'). Some names describe actions, some describe output formats. While most are verb_noun snake_case, the verbs vary in style (get, list, search, audit, preview, check, verify, create, suggest) and some names are compound like 'preview_reverse_estimate' and 'create_ap2_fairness_attestation', which are not predictable.
14 tools is well within the ideal 3-15 range and each tool serves a distinct role in the estimate-fairness ecosystem: price lookup, auditing, red flags, integrity verification, AP2 bridge, and agent discovery. The count feels appropriate for the server's specialized purpose.
The server covers the core workflow well: browse categories, search categories, get price range, audit an estimate, preview direction, check red flags, verify fairness, and create/verify attestations. Minor gaps include a tool for directly comparing two estimates or a dedicated tool to explain the PTKA concept in more depth, but agents can work around these using existing tools and descriptions.