About keywordminer
keywordminer provides Marketing Miner Profiler analytics through MCP tools and a CLI. It covers keyword metrics and suggestions, plus website traffic estimates and historical comparisons.
Key features
- 01Single and batch keyword metrics
- 02Keyword suggestions with pagination
- 03Website traffic estimates
- 04Historical trends and competitor comparison
- 05Markdown or JSON responses
Use cases
- 01Check search volume and CPC
- 02Find keyword suggestions by type
- 03Review website traffic over time
- 04Compare traffic with competitors
MCP support
Exposes Marketing Miner tools for keyword metrics and suggestions, website statistics, and historical traffic ranges. Calls require a Marketing Miner API token.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
5Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| lang | string | Yes | Market/language code, e.g. "cs", "sk", "pl", "hu", "ro", "gb", or "us" |
| keyword | string | Yes | The keyword to look up |
| response_format | enum | No | Response format: "markdown" (default, human-readable) or "json"markdown | json |
Details
From the project READMEkeywordminer
Keyword and website analytics from the Marketing Miner
Profilers API, packaged as MCP tools: search volume, CPC,
year-over-year change and seasonality for single keywords or
batches of up to 1000, keyword suggestions (questions / new /
trending, paginated), and website traffic estimates with a
historical range and optional competitor comparison. Markets:
cs, sk, pl, hu, ro, gb, us.
Every tool takes an optional response_format: markdown
(the default) renders a readable summary of the API payload;
json returns the API JSON as structured text.
Configuration
The API token comes from the environment:
MARKETING_MINER_API_TOKEN(alternates:MARKETING_MINER_API_KEY,MARKETING_MINER_TOKEN,MM_API_TOKEN,MM_API_KEY)
With no token set, every call returns an honest error naming
MARKETING_MINER_API_TOKEN — no data is ever fabricated. The
upstream base defaults to
https://profilers-api.marketingminer.com and can be
overridden with MARKETING_MINER_API_BASE.
CLI
export MARKETING_MINER_API_TOKEN=...
npx @reneturcios/keywordminer search-volume cs "seo nastroje"
npx @reneturcios/keywordminer search-volume us "running shoes" --json
npx @reneturcios/keywordminer --version
Exit codes: 0 on success, 1 on a runtime error (including
a missing token or an upstream HTTP error), 2 on a usage
error.
MCP server
npx -y @reneturcios/keywordminer mcp
MCP client config:
{
"mcpServers": {
"keywordminer": {
"command": "npx",
"args": ["-y", "@reneturcios/keywordminer", "mcp"],
"env": { "MARKETING_MINER_API_TOKEN": "..." }
}
}
}
Tools
marketing_miner_get_search_volume— search volume for one keyword.lang,keyword(required);response_format. Upstream:GET /keywords/search-volume-data.marketing_miner_batch_search_volume— search volume for a batch.lang,keywords(required);response_format. Upstream:POST /keywords/search-volume-data.marketing_miner_get_keyword_suggestions— suggestions for a seed keyword.lang,keyword(required);suggestions_type,limit,offset,response_format. Upstream:GET /keywords/suggestions.marketing_miner_get_website_stats— traffic estimates for a target.lang,type,target(required);response_format. Upstream:GET /websites/stats.marketing_miner_get_website_stats_range— historical traffic trend, optionally against competitors.lang,type,target(required);period,competitors,response_format. Upstream:GET/POST /websites/stats-range(POST when competitors are given).
Docker
docker run -i -e MARKETING_MINER_API_TOKEN=... ghcr.io/cloudcorprecords/keywordminer
Development
npm install
npm run build # tsc -> dist/
npm test # tsx --test test/*.test.ts (fake fetch, no network)
npm run dev # run the CLI from source
License
MIT — Copyright (c) 2026 Rene Turcios
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.