Jackpot Keywords
MCP server for JackpotKeywords — AI keyword research and AI-visibility (AEO) scanning. Three tools: recommend (keywords ranked by composite Jackpot Score using real Google Ads volume/CPC + AI relevance); aeo_scan (10 buyer-intent queries via Gemini grounded search, reports whether your URL is cited/mentioned/absent); credit_balance. Install: npx -y jackpotkeywords-mcp-server
README
jackpotkeywords-mcp-server
MCP (Model Context Protocol) server for JackpotKeywords — AI-powered keyword research and AI-visibility scanning. Lets Claude Code, Claude Desktop, Cursor, Windsurf, and other MCP-compatible clients call JackpotKeywords directly.
Three tools available: jackpotkeywords_credit_balance, jackpotkeywords_recommend, jackpotkeywords_aeo_scan.
Prerequisites
- A JackpotKeywords API key — generate one at https://jackpotkeywords.web.app/developers (instant, self-serve, $5 starter credit, no card required).
- Node.js 18 or newer (only if installing locally;
npxdoesn't require a local Node.js if your MCP client bundles one).
Configure in Claude Code
Recommended — use the CLI:
claude mcp add -s user jackpotkeywords \
-e JACKPOTKEYWORDS_API_KEY=jk_live_... \
-- npx -y jackpotkeywords-mcp-server
That writes the server to your user-scope config (~/.claude.json) so it's available in every Claude Code session, in every project. Verify with claude mcp list.
Or hand-edit ~/.claude.json (user scope) or .mcp.json in the project root (project scope), adding to the mcpServers object:
{
"mcpServers": {
"jackpotkeywords": {
"command": "npx",
"args": ["-y", "jackpotkeywords-mcp-server"],
"env": {
"JACKPOTKEYWORDS_API_KEY": "jk_live_..."
}
}
}
}
Important: Claude Code does not read ~/.claude/mcp.json (with the slash). The real user-scope path is ~/.claude.json (with the dot). Use the CLI to avoid this trap.
Restart any open Claude Code session to pick up the new tools — MCP servers load at session start, not dynamically.
Configure in Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"jackpotkeywords": {
"command": "npx",
"args": ["-y", "jackpotkeywords-mcp-server"],
"env": {
"JACKPOTKEYWORDS_API_KEY": "jk_live_..."
}
}
}
}
Configure in Cursor
Cursor uses the same JSON shape. Settings → MCP → Add Server:
{
"mcpServers": {
"jackpotkeywords": {
"command": "npx",
"args": ["-y", "jackpotkeywords-mcp-server"],
"env": { "JACKPOTKEYWORDS_API_KEY": "jk_live_..." }
}
}
}
Tools
jackpotkeywords_credit_balance
Returns the current credit balance for your API account.
No arguments. Use it to verify your key works and to check credits before calling the paid tools.
jackpotkeywords_recommend
Runs the full keyword research pipeline for a product and returns ranked recommendations by composite Jackpot Score (volume, CPC, competition, trend, cluster strength, AI relevance). Backed by real Google Ads Keyword Planner data.
Cost: $0.10 per call (flat — regardless of limit). Refunded on pipeline failure. Latency ~60–180s.
| Argument | Type | Required | Description |
|---|---|---|---|
url |
string | one-of | Product URL to extract context from |
description |
string | one-of | Plain-English product description |
limit |
number | no | Max recommendations to return. Default 50, max 200. |
budget |
number | no | Daily ad budget in USD (influences AI scoring) |
location |
string | no | Location for local-intent boosting |
Returns: top 25 recommendations as a readable table in content, with the full ranked list in structuredContent.recommendations.
Example prompt (in Claude Code):
Use jackpotkeywords_recommend on https://bulklistingpro.com — find keywords I should target for SEO and Google Ads for an eBay bulk listing tool. Limit 50.
jackpotkeywords_aeo_scan
Runs an AI-visibility scan. Asks 10 buyer-intent queries about your product through Gemini's grounded search and reports, per query: whether the URL was cited as a source, mentioned in the answer text, or absent — plus the top sources the AI did cite.
Cost: $1.00 per scan (refunded on failure). Latency ~30–120s.
| Argument | Type | Required | Description |
|---|---|---|---|
url |
string | yes | Product URL to scan |
productContext |
object | no | Pre-extracted product context (skip extraction step) |
Returns: visibility score + per-query results in content, full structured data in structuredContent.queries.
Example prompt:
Run jackpotkeywords_aeo_scan on https://markitup.app and tell me which queries we're missing from.
Environment variables
| Var | Required | Description |
|---|---|---|
JACKPOTKEYWORDS_API_KEY |
yes | API key from https://jackpotkeywords.web.app/developers |
JACKPOTKEYWORDS_API_BASE |
no | Override the API base URL. Default: https://jackpotkeywords.web.app/api/v1. Useful for testing against staging. |
Pricing reference
$5 starter crediton signup (no card, no expiration)/v1/recommend— $0.10/call (≈ 50 calls per $5)/v1/aeo-scan— $1.00/call (≈ 5 calls per $5)- Topup via Stripe checkout (
POST /v1/topup) in $25 / $100 / $500 packs or custom ≥ $25 - Rate limit: 60 requests/min, 1000/hr per key
Local development
git clone https://github.com/smythmyke/jackpotkeywords-mcp-server.git
cd jackpotkeywords-mcp-server
npm install
npm run build
# Point your MCP client config at the local build:
{
"command": "node",
"args": ["/absolute/path/to/jackpotkeywords-mcp-server/dist/index.js"],
"env": { "JACKPOTKEYWORDS_API_KEY": "jk_live_..." }
}
Security
- Never commit
JACKPOTKEYWORDS_API_KEYto source control. - If you accidentally expose a key, revoke it at https://jackpotkeywords.web.app/developers and create a new one (
POST /v1/keys+DELETE /v1/keys/:keyId). - Keys are SHA-256 hashed on the server; the raw key is shown only once at creation.
Errors
The server surfaces clean human-readable errors for the common cases:
Invalid or missing JACKPOTKEYWORDS_API_KEY— set or rotate the key.Insufficient balance— top up at https://jackpotkeywords.web.app/developers.Rate limit exceeded— wait briefly and retry.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.