Pricing Data: SaaS, AI & LLM Cost API | ComparEdge MCP Server
@comparedge
基本情報
Pricing Data: SaaS, AI & LLM Cost API | ComparEdge MCP Server について
Free REST API and MCP server for verified SaaS, AI, and LLM pricing across 490+ tools. OpenAPI 3.1, no API key.

Pricing Data: SaaS, AI & LLM Cost API | ComparEdge MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"comparedge": {
"command": "npx",
"args": [
"-y",
"@comparedge/mcp-server"
]
}
}
}Pricing Data: SaaS, AI & LLM Cost API | ComparEdge MCP Server のツール
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
概要
What this gives you
Software pricing is published to be hard to compare. Tiers hide the number that matters, add-ons live on a different page, and the first-year rate is not the rate you renew at. This server carries that data already read and structured: 495 SaaS and AI products across 44 categories, taken from vendor pricing pages and re-checked on a schedule, with the verification date attached to every record.
Nine tools, over plain HTTP, no key and no signup.
Tools
| Tool | What you get |
|---|---|
get_pricing | Every tier of one product with what each includes, the price range, annual discount, hidden costs and a verdict |
compare_software | Two to four products side by side, full records plus a compact matrix of starting price, free tier, max annual discount and hidden costs |
discover_software | Find tools by category, budget ceiling, free-tier requirement or keyword, with the source link on each card |
get_hidden_costs | Implementation, add-ons, overage and support: the money that is not on the pricing page |
calculate_tco | Total cost for a real team, seat-aware and billing-aware, subscription line plus hidden-cost line items |
estimate_llm_cost | Per-model rate card in dollars per million tokens, input, output, cached input and context window, plus an estimate for your volume |
get_cost_guide | Negotiation brief: real renewal rates, the vendor's cost-transparency score, and which discount programs survive renewal |
get_price_history | Latest verified snapshot, last observed change and the derived trend |
get_positioning | Where a product sits against its category on price: median, min, max and sample size |
Connect over HTTP
No install, no credential. Point any MCP client at the endpoint:
{
"mcpServers": {
"comparedge": {
"url": "https://comparedge.com/api/mcp"
}
}
}
Or talk to it directly:
curl -s -X POST https://comparedge.com/api/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Or run it locally
Three packages, each with its own job:
{
"mcpServers": {
"comparedge": {
"command": "npx",
"args": ["-y", "@comparedge/mcp-server"]
},
"comparedge-price-watch": {
"command": "npx",
"args": ["-y", "@comparedge/price-watch-mcp"]
},
"comparedge-llm-cost": {
"command": "npx",
"args": ["-y", "@comparedge/llm-cost-mcp"]
}
}
}
mcp-server is the catalogue: pricing, alternatives and feature comparisons.
price-watch-mcp tracks what moved: recent changes, per-product history, category trends and the
biggest increases, from a human-reviewed change log.
llm-cost-mcp prices token workloads against verified per-million rates for 60+ models from 16+
providers.
What it is good for
Sizing a renewal before the call, so you know the number the vendor is about to quote you. Budgeting an LLM feature at real token volume instead of a guess. Answering "what does X cost" without landing on a pricing page that says Contact Sales. Building a comparison that cites a verification date rather than a vibe.
Where the numbers come from
Vendor pricing pages, read and re-checked on a schedule, with the date recorded per product. Where a vendor publishes nothing, the record says so rather than estimating. Where a price comes from a marketplace listing rather than the vendor's own page, it is marked and does not count as disclosed.
FAQ
Do I need an API key? No. The HTTP server is open and CORS-enabled. There is no signup and no rate-limit tier to buy.
How current is the data? Every product carries its own verification date, returned with the record. Re-checks run on a schedule rather than on request, so you see when a number was last confirmed instead of trusting that it is fresh.
What happens when a vendor hides its pricing? The record says the tier is quote-only. Nothing is estimated to fill the gap, and a figure taken from a marketplace listing is flagged as such rather than passed off as the vendor's own.
Is there a REST API too? Yes, same data, OpenAPI 3.1, documented at https://comparedge.com/api-docs.
Which categories are covered? 44, including CRM, project management, cloud hosting, databases, IAM, compliance, payments, design, SEO, ERP, and the AI families: LLMs, coding, image, video, voice, agents.
「データと分析」の他のコンテンツ

TofuBofu AI Visibility
Arnav NeilTofuBofu runs a free AI visibility scan for any B2B company, right inside your AI assistant. Ask it to scan a domain and it runs the questions real buyers ask across ChatGPT, Claude, Gemini, Perplexity, Google AI Overvie
SiteGuru
Your site's real SEO data in your AI assistant. SiteGuru crawls your website and connects to Google Search Console and Google Analytics. This server exposes that data to your assistant, so you can ask what's broken, wha

PermitIntel
PermitIntel.aiBuilding permit data and Florida contractor license checks over MCP. 81.8M permit records from the cities and counties that issue them, across 51 states. Four tools: verify_license, search_permits, lookup_contractor, roo
Sugra API MCP
Sugra Systems, Inc.Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl

Tracetify — Competitor Ads, Growth Traces & Search Console
tracetify17 tools for marketing and SEO research inside Claude Code, Cursor, Codex or ChatGPT: the ads any domain runs on Meta and Google, how a product grew from 12 public sources with every claim linked, your own Search Console
コメント