Jungle Scout for AI agents

Jungle Scout gives Amazon sellers product research and sales estimate data to optimize pricing and listings. Merchants use it to run this as a routine part of their storefront operations. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

E-commerceAPI keyMCP + RESTjunglescout.com
AUDIT LOG · JUNGLE SCOUTPOLICY: acme-support
09:41:07 · claude · u_8f2read
jungle_scout.query_the_product_database
Query the product database✓ allowed · 212ms
09:41:08 · claude · u_8f2read
jungle_scout.retrieve_share_of_voice_data
Retrieve share of voice data✓ allowed · 164ms
09:41:09 · claude · u_8f2write
jungle_scout.keyword_historical_volume
Retrieve historical search volume data for a keyword✓ approved · approved by user
EVERY JUNGLE SCOUT CALL, ON THE RECORD
01 · USE CASES

What agents do in Jungle Scout.

01

Check keyword search volume

Pull historical search volume for a keyword to decide whether to target it in a listing.

02

Estimate sales for a product

Pull sales estimate data for a competitor's ASIN to gauge market demand.

03

Query the product database

Query the product database for items matching a category and price range for research.

02 · ACTIONS

6 Jungle Scout actions, graded by risk.

Every Jungle Scout action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • jungle_scout.query_the_product_database
    Query the product database
  • jungle_scout.retrieve_share_of_voice_data
    Retrieve share of voice data
  • jungle_scout.retrieve_sales_estimates_data
    Retrieve sales estimates data
  • jungle_scout.retrieve_keyword_data_for_specified_asins
    Retrieve keyword data for specified asins
  • jungle_scout.retrieve_data_for_a_specific_keyword_query
    Retrieve data for a specific keyword query

write

1

Create and change things. Allow, or ask the user first.

  • jungle_scout.keyword_historical_volume
    Retrieve historical search volume data for a keyword

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Jungle Scout in three steps.

  1. 01Your users connect Jungle ScoutThey add their Jungle Scout api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “retrieve historical search volume data for a keyword” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Jungle Scout through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('jungle_scout', {
  read: 'allow',
  write: 'ask',        // keyword_historical_volume
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Jungle Scout connects.

Users add their Jungle Scout api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Jungle Scout connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Jungle Scout from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Jungle Scout and Arc0, answered.

Q01

Can I use Jungle Scout with Claude, ChatGPT or Cursor?

Yes. Connect Jungle Scout to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Jungle Scout actions you allow.

Q02

How do users connect Jungle Scout?

Users add their Jungle Scout api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Jungle Scout actions can my agent take?

6 in total: 5 read, 1 write and 0 destructive, such as “retrieve historical search volume data for a keyword”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Jungle Scout?

Yes. Allow read actions and deny writes in the Jungle Scout policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Jungle Scout too?

Yes. The same Jungle Scout connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Jungle Scout into your agent.

Your users connect Jungle Scout once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan