Junglescout Mcp

io.github.purahmanianPublished by GitHub account purahmanianv0.1.1Updated Oct 24, 2026

Jungle Scout MCP server: keyword volumes, product database, sales estimates, share of voice

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

Local MCP server that lets an assistant query the Jungle Scout API for Amazon keyword volumes, listing keywords, product searches, sales estimates and brand-shu

What you can do
Look up Amazon keyword search volume, trends and PPC bid estimates for up to 100 keywords at a time, with exact and broad match data and 30-day and quarterly trends. Find the keywords driving traffic to a specific ASIN, including organic and sponsored positions. Search the product database by category, title keywords, price, minimum revenue and maximum reviews to surface product opportunities. Estimate monthly units sold and revenue for an ASIN. Measure brand share of organic and sponsored results for a keyword.
When to use it
Useful for Amazon sellers, product researchers and e-commerce analysts who want to do keyword research, competitor keyword gap analysis and product opportunity discovery conversationally, provided they already have Jungle Scout API access.
Requirements
Runs locally via npx (Node.js). Needs an active Jungle Scout subscription that includes Developer/Cobalt API access, plus two environment variables: JUNGLESCOUT_API_KEY and JUNGLESCOUT_KEY_NAME. Network access to the Jungle Scout API is required. Without credentials the server starts but tools return setup instructions.
Before you install
Requires your Jungle Scout API key and key name; they are sent only to the Jungle Scout API and are not stored on disk. The server is unofficial and not affiliated with or endorsed by Jungle Scout. Queries send the keywords and ASINs you ask about to Jungle Scout. API access depends on a paid Jungle Scout plan.

Installation

In SourceWeft

  1. Open Junglescout Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

junglescout-mcp

MCP server for the Jungle Scout Cobalt/Developer API: keyword search volume, ASIN keyword analysis, product database queries, sales estimates, and share of voice.

[CI] [npm]


Unofficial: This project is not affiliated with, endorsed by, or sponsored by Jungle Scout. "Jungle Scout" is a trademark of Jungle Scout Group LLC. All rights belong to their respective owners.


What it does

ToolDescriptionExample prompt
keyword_search_volumeExact-match and broad-match volume for up to 100 keywords, plus 30-day trend, quarterly trend, and PPC bid estimates"What is the search volume for 'yoga mat' and 'foam roller' on Amazon?"
keywords_by_asinWhich keywords drive traffic to a specific Amazon listing"What keywords is ASIN B07XJ8C8F5 ranking for?"
product_database_queryFind product opportunities filtered by category, title keywords, price, minimum revenue, and max reviews"Find Sports and Outdoors products under $40 with at least $5k monthly revenue and fewer than 300 reviews"
sales_estimatesEstimated monthly units sold and revenue for an ASIN"How many units per month does B07XJ8C8F5 sell?"
share_of_voiceBrand share of organic and sponsored results for a keyword"Which brands dominate the 'protein powder' keyword on Amazon?"

Quick start

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "junglescout": {      "command": "npx",      "args": ["-y", "junglescout-mcp"],      "env": {        "JUNGLESCOUT_API_KEY": "your-api-key-here",        "JUNGLESCOUT_KEY_NAME": "your-key-name-here"      }    }  }}

Restart Claude Desktop after saving.

Claude Code

bash
claude mcp add junglescout \  -e JUNGLESCOUT_API_KEY=your-api-key-here \  -e JUNGLESCOUT_KEY_NAME=your-key-name-here \  -- npx -y junglescout-mcp

OpenAI Codex CLI

Add to ~/.codex/config.toml:

toml
[mcp_servers.junglescout]command = "npx"args = ["-y", "junglescout-mcp"]
[mcp_servers.junglescout.env]JUNGLESCOUT_API_KEY = "your-api-key-here"JUNGLESCOUT_KEY_NAME = "your-key-name-here"

Getting an API key

The Jungle Scout Developer API requires an active Jungle Scout subscription that includes API access.

Sign up or upgrade your Jungle Scout plan: https://www.junglescout.com/pricing/

Once you have a plan with API access:

  1. Log in to Jungle Scout and navigate to Settings > Manage API Keys.
  2. Create a new API key. You will receive both a Key Name and an API Key.
  3. Set the environment variables:
bash
export JUNGLESCOUT_API_KEY="your-api-key-here"export JUNGLESCOUT_KEY_NAME="your-key-name-here"

The server will start without credentials and tools will return setup instructions until both variables are configured.


Example conversations

Keyword research for a new product:

"Give me the Amazon US search volume and PPC bid estimates for 'bamboo cutting board', 'wooden cutting board', and 'plastic cutting board'. Which has the best volume-to-competition ratio?"

The model calls keyword_search_volume with all three terms, compares volumes and ease-of-ranking scores, and summarizes which keyword is the best entry point.

Competitor keyword gap analysis:

"I am competing with ASIN B07XJ8C8F5. What are the top 20 keywords driving traffic to that listing?"

The model calls keywords_by_asin and returns the ranking keywords sorted by relevancy, including organic and sponsored positions.

Product opportunity discovery:

"Find me product opportunities in the Kitchen category priced between $20 and $60 with at least $8,000 monthly revenue and fewer than 150 reviews."

The model calls product_database_query with the filters and returns a ranked list of products with revenue, BSR, and listing quality scores.


Development

bash
# Install dependenciesnpm install
# Run tests (no live API calls)npm test
# Buildnpm run build
# Run locally (credentials required for live data)JUNGLESCOUT_API_KEY=xxx JUNGLESCOUT_KEY_NAME=yyy node dist/index.js

Authentication

The Jungle Scout API uses a custom authorization format:

Authorization: <KEY_NAME>:<API_KEY>X-API-Type: junglescoutContent-Type: application/vnd.api+jsonAccept: application/vnd.junglescout.v1+json

The Accept header selects the API version and must be the application/vnd.junglescout.v1+json media type. Sending a different Accept value causes the API to return HTTP 404.

All marketplace parameters default to us. Other supported values include ca, uk, de, fr, it, es, jp, au, in, and more.


Built by

Built by Puya Ventures LLC. I build custom MCP servers and AI integrations for product, e-commerce, and data teams. Get in touch: [email protected] | Portfolio: puyarahmanian.com

Part of the Product-Research MCP Suite: keepa-mcp · google-trends-mcp · junglescout-mcp


Privacy

This server runs entirely on your machine. It collects no telemetry and stores no data. The only network calls it makes are to the Jungle Scout API (developer.junglescout.com), sending your API credentials and the keywords or ASINs you ask about. Credentials are read from the JUNGLESCOUT_API_KEY and JUNGLESCOUT_KEY_NAME environment variables and never written to disk or sent anywhere except Jungle Scout. See Jungle Scout's privacy policy: https://www.junglescout.com/privacy/

License

MIT. See LICENSE.

Source: README.md at commit 0341f4a

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts