{
  "markdown": "# Amazon knowledge retrieval MCP server (Amazon Agent Atlas) by Kuudo\n\nA retrieval layer your agent checks before it answers. It indexes Amazon operating knowledge across Ads, Seller Central, and Vendor Central.\n\n[![MCP](https://img.shields.io/badge/MCP-Model%20Context%20Protocol-8A2BE2?style=flat-square)](https://modelcontextprotocol.io/) [![Registry](https://img.shields.io/badge/MCP%20Registry-io.github.KuudoAI%2Famazon--agent--atlas--mcp-blue?style=flat-square)](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.KuudoAI%2Famazon-agent-atlas-mcp&version=latest) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](LICENSE) [![Community](https://img.shields.io/badge/Kuudo-community-D97757?style=flat-square)](https://github.com/KuudoAI/community)\n\nProduct page: https://www.kuudo.com/features/agent-atlas/ · Docs: https://www.kuudo.com/docs/amazon-agent-atlas/ · Pricing: https://www.kuudo.com/pricing.md\n\n## Connect\n\nKuudo 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:\n\n```json\n{\n  \"mcpServers\": {\n    \"amazon-agent-atlas-mcp\": {\n      \"url\": \"https://<your-host>/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer <your Kuudo API key>\"\n      }\n    }\n  }\n}\n```\n\nReplace `<your-host>` with the hostname of your deployment and the bearer value with your Kuudo API key.\n\nA 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.\n\n## What this repository is\n\nThis 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.\n\n### Inspect the catalog locally with Docker\n\nThe image runs the same catalog-only stub over stdio. It is not the live server.\n\n```bash\ndocker build -t amazon-agent-atlas-mcp .\ndocker run -i --rm amazon-agent-atlas-mcp\n```\n\nPoint a client at it with a stdio entry:\n\n```json\n{\n  \"mcpServers\": {\n    \"amazon-agent-atlas-mcp-catalog\": {\n      \"command\": \"docker\",\n      \"args\": [\"run\", \"-i\", \"--rm\", \"amazon-agent-atlas-mcp\"]\n    }\n  }\n}\n```\n\n## Tools\n\n4 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.\n\nEach 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.\n\n<details>\n<summary>Every tool (4)</summary>\n\n| Tool | Access | What it does |\n| --- | --- | --- |\n| `tags` | read | List available tool tags. Use to browse available tools by tag before searching. |\n| `search` | read | Search for available tools by query. Returns matching tools ranked by relevance. |\n| `get_schema` | read | Get parameter schemas for specific tools. Use after searching to get the detail needed to call a tool. |\n| `execute` | write | Chain `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. |\n\n</details>\n\n## Set up your client\n- [Quick Start: Activepieces MCP](https://www.kuudo.com/docs/quick-start/activepieces/)\n- [Quick Start: Google Antigravity](https://www.kuudo.com/docs/quick-start/antigravity/)\n- [Quick Start: ChatGPT Skills](https://www.kuudo.com/docs/quick-start/chatgpt-skills/)\n- [Quick Start: ChatGPT](https://www.kuudo.com/docs/quick-start/chatgpt/)\n- [Quick Start: Claude](https://www.kuudo.com/docs/quick-start/claude-ai/)\n- [Quick Start: Claude Skills](https://www.kuudo.com/docs/quick-start/claude-app-skills/)\n- [Quick Start: Claude Code MCP](https://www.kuudo.com/docs/quick-start/claude-code-mcp/)\n- [Quick Start: Claude Cowork for Amazon Workflows](https://www.kuudo.com/docs/quick-start/claude-cowork-amazon/)\n- [Quick Start: Claude Code Skills](https://www.kuudo.com/docs/quick-start/claude-skills/)\n- [Quick Start: Codex Skills](https://www.kuudo.com/docs/quick-start/codex-skills/)\n- [Quick Start: Codex](https://www.kuudo.com/docs/quick-start/codex/)\n- [Quick Start: Hermes MCP](https://www.kuudo.com/docs/quick-start/hermes/)\n- [Quick Start: Lovable](https://www.kuudo.com/docs/quick-start/lovable/)\n- [Quick Start: n8n MCP](https://www.kuudo.com/docs/quick-start/n8n/)\n- [Quick Start: NanoClaw MCP](https://www.kuudo.com/docs/quick-start/nanoclaw/)\n- [Quick Start: OpenAI API](https://www.kuudo.com/docs/quick-start/openai-api/)\n- [Quick Start: OpenClaw MCP](https://www.kuudo.com/docs/quick-start/openclaw/)\n- [Quick Start: Perplexity MCP](https://www.kuudo.com/docs/quick-start/perplexity/)\n\n## Reads, writes, approvals\n\nRead 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`.\n\n## Kuudo\n\n- Website: https://www.kuudo.com/\n- Docs: https://www.kuudo.com/docs/\n- Guides: https://www.kuudo.com/guides/\n- Community, bugs, and questions: https://github.com/KuudoAI/community\n- Roadmap: https://github.com/orgs/KuudoAI/projects\n- Machine-readable: https://www.kuudo.com/llms.txt · https://www.kuudo.com/pricing.md\n\nGenerated from KuudoAI/marketing. Do not edit by hand; changes are overwritten on the next sync.\n",
  "bytes": 5981,
  "sha": "45227125c0ceb2a6dd62a9c71748179284b3826781b6fe04f6fec49587eb63dc",
  "repo_slug": "kuudoai/amazon-agent-atlas-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_kuudoai_amazon_agent_atlas_mcp_c3e47538/readme"
}