Amazon knowledge retrieval MCP server (Amazon Agent Atlas)

io.github.KuudoAIPublished by GitHub account KuudoAIv1.0.0Updated Oct 24, 2026

MCP retrieval server for indexed Amazon Ads, Seller Central, and Vendor Central knowledge.

The publisher's own server: Red Atlas Api

VerifiedStreamable HTTPWeb executableKnowledge & MemoryBusiness & Commerce

Overview

AI-generated overview

Remote MCP retrieval layer that lets an assistant browse, search and run indexed Amazon Ads, Seller Central and Vendor Central knowledge tools.

What you can do
  • Browse and search the tool catalog by tag or query, with results ranked by relevance
  • Read parameter schemas for specific tools before calling them
  • Chain tool calls in one sandboxed Python block and return the final value
  • Inspect the catalog offline through a catalog-only stub that serves the tool list, a catalog resource and a connect prompt
When to use it
Useful when an assistant needs grounded Amazon operating knowledge across Ads, Seller Central and Vendor Central before answering, and you already run a Kuudo deployment in your own cloud.
Requirements
A remote streamable HTTP endpoint at your own Kuudo deployment host, plus an Authorization header carrying a Kuudo API key or deployment bearer token. Some tools may document their own separate provider credentials. The published repository is only a catalog stub; live execution runs in the deployment.
Before you install
The Authorization header carries a Kuudo API key or bearer token, so treat it as a secret. The execute tool is marked as a write tool and runs Python in a sandbox with time, memory and import limits. Provider credentials for individual tools are separate from the bearer. The server source is not published, and the public stub returns errors rather than real Amazon data.

Installation

In SourceWeft

  1. Open Amazon knowledge retrieval MCP server (Amazon Agent Atlas) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Follow the launch instructions in the repository.

README

Amazon knowledge retrieval MCP server (Amazon Agent Atlas) by Kuudo

A retrieval layer your agent checks before it answers. It indexes Amazon operating knowledge across Ads, Seller Central, and Vendor Central.

[MCP] [Registry] [License: MIT] [Community]

Product page: https://www.kuudo.com/features/agent-atlas/ · Docs: https://www.kuudo.com/docs/amazon-agent-atlas/ · Pricing: https://www.kuudo.com/pricing.md

Connect

Kuudo runs in your own cloud. The Community plan deploys one instance of each Amazon MCP server into your account, and your client connects to that deployment:

json
{  "mcpServers": {    "amazon-agent-atlas-mcp": {      "url": "https://<your-host>/mcp",      "headers": {        "Authorization": "Bearer <your Kuudo API key>"      }    }  }}

Replace <your-host> with the hostname of your deployment and the bearer value with your Kuudo API key.

A tool may document a provider credential of its own. That is separate from the bearer above, it belongs to the service the tool calls, and the tool's own entry says so.

What this repository is

This repository holds registry metadata and a catalog-only stub. Live execution runs in your Kuudo deployment. The server source is not published. The stub in src/ answers tools/list with the catalog below, serves the same catalog as one resource (kuudo://catalog/tools.json), offers one prompt (connect) carrying the setup guidance, and returns an error with that guidance on any call, so registries and clients can inspect the surface without any access to Amazon.

Inspect the catalog locally with Docker

The image runs the same catalog-only stub over stdio. It is not the live server.

bash
docker build -t amazon-agent-atlas-mcp .docker run -i --rm amazon-agent-atlas-mcp

Point a client at it with a stdio entry:

json
{  "mcpServers": {    "amazon-agent-atlas-mcp-catalog": {      "command": "docker",      "args": ["run", "-i", "--rm", "amazon-agent-atlas-mcp"]    }  }}

Tools

4 tools, read from a running instance of this server. Four tools front the whole corpus: browse tags, search, read a schema, then run a chained call.

Each tool carries the argument schema the live server publishes, so a client can inspect the full call signature here before it connects to your deployment.

Every tool (4)
ToolAccessWhat it does
tagsreadList available tool tags. Use to browse available tools by tag before searching.
searchreadSearch for available tools by query. Returns matching tools ranked by relevance.
get_schemareadGet parameter schemas for specific tools. Use after searching to get the detail needed to call a tool.
executewriteChain await call_tool(...) calls in one Python block and return the final value. Only call_tool(tool_name: str, params: dict) -> Any is available as an external function. Supported imports: asyncio, datetime, json, math, os, pathlib, re, sys, typing. Other standard-library and third-party imports, including collections, are unavailable in the sandbox. Use f-strings because str.format is unavailable. Limits: 10 seconds, 50,000,000 bytes of memory, and recursion depth 100.

Set up your client

Reads, writes, approvals

Read tools are safe to call freely. Write tools do work inside your deployment and never change anything on Amazon. Each tool's access is recorded beside it in tools.json.

Kuudo

Generated from KuudoAI/marketing. Do not edit by hand; changes are overwritten on the next sync.

Source: README.md at commit ce6bc9c

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

60% 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 daysRequired25 pts

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

  • Auth declaredRequired10 pts
  • 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

Other Atlas integrations