price-watch
About
Verified SaaS price-change history and watch-log for AI assistants. Data by ComparEdge. Free, no API key.
Details
- Author
- comparedge
- GitHub stars
- 1
- Downloads
- 375
- Categories
- Finance, Search, Infrastructure
Jump to
- Recent price moves across the whole catalog, filterable by period.
- Full dated change history for a single product.
- Category-level pulse: which markets are drifting up.
- The biggest recorded increases, for renewal negotiations.
- Current verified price check for any tracked product.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
price-watchCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add npx -y @comparedge/price-watch-mcp@latest to your MCP client config (Claude Desktop, Cursor, VS Code) and restart. Five tools and three prompts appear. No API key, no account.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"price-watch": {
"price-watch": {
"command": "npx",
"args": [
"-y",
"@comparedge/price-watch-mcp@latest"
]
}
}
}
}McpServers
{
"price-watch": {
"command": "npx",
"args": [
"-y",
"@comparedge/price-watch-mcp@latest"
]
}
}Verified SaaS price-change history and watch-log for AI assistants. Data by ComparEdge. Free, no API key.
@ the log, two real entries surfshark / Starter vpn 2026-05-30 - $2.49 + $15.45 bluehost / Basic cloud-hosting 2026-07-06 - $1.99 + $3.99
That first row is a 520 percent jump on an intro rate that quietly expired. Nobody mails you about these. This MCP server hands an assistant the reviewed log of every move like it, so "did this get more expensive" stops being a guess.
The log sits behind thepricing database, 494 tools deep. Dated rows, old and new values where a price moved, a human sign-off on each. The 30 days to July 10, 2026 carried 636 entries, 120 of them outright price moves.
The week of July 6, verbatim from the feed.Bluehost raised Basic from $1.99 to $3.99. Screaming Frog cut its paid tier from $279 to $199. Namecheap dropped Stellar to $2.28. Chargebee re-read Starter as free where it used to say $250 a month. Binance refreshed its spot maker and taker schedule, and Coinbase touched both Advanced Trade fees and the Coinbase One tiers.
bluehost / Basic cloud-hosting 2026-07-06 - $1.99 + $3.99 screaming-frog / Paid seo-tools 2026-07-06 - $279 + $199 namecheap / Stellar cloud-hosting 2026-07-06 - $4.66 + $2.28 chargebee / Starter payments 2026-07-08 - $250/mo + free
Hosting swings hardest week to week; intro rates expire, renewal ladders kick in, and the log catches each step with a date.
Did Notion change anything this quarter?product_changesreturns dated rows for one slug. Notion right now: quiet quarter, last verified July 4. The human-readable trail is itsprice historypage.
What went up the most this month?biggest_increasesranks the sharpest hikes in a window. Surfshark's intro-rate expiry tops the current one.
Is anything moving in cloud hosting?category_changessweeps one category. Hosting logged three moves in the first week of July alone.
What does Framer charge today, and is that new?check_pricereturns the current verified price plus the last change touching it.recent_changesis the same idea for the whole catalog, newest first.
sequenceDiagram participant A as Assistant participant S as price-watch participant F as changelog feed A->>S: biggest_increases, last 30 days S->>F: fetch once, cache 6h F-->>S: 636 dated entries S-->>A: ranked hikes, old and new prices, dates Note over A: answer cites dates,<br/>not vibes
{ "mcpServers": { "price-watch": { "command": "npx", "args": ["-y", "@comparedge/price-watch-mcp@latest"] } } }
Claude Desktop reads~/Library/Application Support/Claude/claude_desktop_config.json, Cursor takes it under Settings then MCP, VS Code with Copilot uses.vscode/mcp.json. Restart the client and five tools show up. No key, no signup, zero dependencies. Client walkthroughs sit in thesetup docs.
Every row passed the sameverification processbefore it landed; the feed carries each sign-off date. Month-by-month roundups of the same data become thepricing reports, and the raw rows ship asopen pricing dataunder CC BY 4.0.
The server fetches two public feeds fromcomparedge.com, caches them for six hours, filters everything on your machine, and serves the last good copy if a refresh fails. The catalog sibling and the token-cost sibling live under the sameMCP familyroof.
Bridge Town is an MCP-native, git-versioned financial modeling platform for FP&A teams and finance leaders. AI agents use Bridge Town tools to create projects, write Python model files, run models in isolated cloud sandboxes, query data, write outputs to Google Sheets, create dashboards, branch scenarios, and collaborate with teammates.
The Capital.com MCP Server lets your AI assistant talk to your trading account directly. Market data, position checks, trade previews – all in plain language, without leaving your AI tool.
Coinrule Agentic Trading MCP enables investors to create, backtest, execute, and manage trading agents through natural language across stocks, crypto and ETFs
Invest with Claude and other AI assistants
Australian Consumer Data Right Product Data
Remote MCP server for historical crypto & prediction-market data: search ~500K instruments, live market stats (OHLC, turnover, spreads, depth, slippage) and tick-data purchase. Keyless for catalog & stats; optional OAuth for account tools. Endpoint: https://cryptostruct.com/mcp
Cross-border debt collection from your AI assistant: check cases, get pricing, submit new cases.
Read-only MCP server for your Evibe investment portfolio + live market data (holdings, performance, dividends, benchmarks, screeners). Works with Claude & ChatGPT.
Financial and quantitative modeling engine for AI agents. Typed, named, deterministic.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
