# How to connect AWS Marketplace MCP to Claude Cowork

```json
{
  "title": "How to connect AWS Marketplace MCP to Claude Cowork",
  "toolkit": "AWS Marketplace MCP",
  "toolkit_slug": "aws_marketplace_mcp",
  "framework": "Claude Cowork",
  "framework_slug": "claude-cowork",
  "url": "https://composio.dev/toolkits/aws_marketplace_mcp/framework/claude-cowork",
  "markdown_url": "https://composio.dev/toolkits/aws_marketplace_mcp/framework/claude-cowork.md",
  "updated_at": "2026-08-06T11:13:24.635Z"
}
```

## Introduction

Cowork is Anthropic's AI agent for knowledge work. Think of it as Claude Code for everything else. It works autonomously with your computer, local files, and applications to accomplish complex tasks.
This guide walks you through the easiest and most secure way to connect your AWS Marketplace account to Cowork via Composio Connect, enabling it to find security tools with free trials, compare Kubernetes monitoring marketplace listings, shortlist data products for analytics teams, and more such actions on your behalf without compromising your account security.

## Also integrate AWS Marketplace MCP with

- [ChatGPT Work](https://composio.dev/toolkits/aws_marketplace_mcp/framework/chatgpt)

## Connect AWS Marketplace MCP to Claude Cowork

### Connecting AWS Marketplace to Claude Cowork
1. Open Customize
In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.
2. Add the Composio MCP server
Click Add custom connector and paste in the Composio MCP server URL:

```bash
https://connect.composio.dev/mcp
```

## What is Claude Cowork?

Claude Cowork is Anthropic's agent for general knowledge work. It can use your computer, files, and connected applications to complete longer-running tasks across your work tools.
With Composio Connect, Cowork can securely access apps like AWS Marketplace through MCP without you sharing account credentials directly with the agent.

## What is the AWS Marketplace MCP server, and what's possible with it?

The AWS Marketplace MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your AWS Marketplace account. It provides structured and secure access so your agent can perform AWS Marketplace operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `AWS_MARKETPLACE_MCP_GET_AWS_MARKETPLACE_RELATED_SOLUTIONS` | Get aws marketplace related solutions | Direct AWS Marketplace Catalog API call. Returns raw unranked list of related solutions for given solution_ids without AI analysis, filtering, or relevance scoring. Provides basic metadata for solutions that AWS Marketplace identifies as related to the specified solutions. **Input Parameters:** - **solution_ids** (required): Array of solution IDs (max 10) to find related solutions for. IDs start with `prodview-`, not `prod-` **Returns:** `{ results: [...] }` - Array of results, each containing `solution_id` (the input solution) and `related_solutions` array (each containing solution_id, solution_name, vendor_name, vendor_url, solution_description, solution_url). **Example:** ```json { "solution_ids": ["prodview-abc123", "prodview-xyz789"] } ``` **Use this tool ONLY when:** - You have solution_ids and need raw related solutions list - Building programmatic integrations requiring unprocessed related solutions data - User explicitly requests raw related solutions API response - Need direct access to AWS Marketplace's related solutions without AI filtering **DO NOT use this tool for:** - Finding alternative solutions → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow - User asking "what are alternatives to [solution]?" → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow - Recommendations or comparisons → Use `get_aws_marketplace_report_guidelines` to get workflow instructions first - Requirements-based alternative discovery → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow **Note:** This is a stateless tool that does not require a conversation or request_id. Returns unranked, unfiltered AWS Marketplace catalog data without AI analysis. **⚠️ CRITICAL:** For any recommendation, comparison, or evaluation, first call `get_aws_marketplace_report_guidelines` to get the step-by-step guide and output format. **CRITICAL: When displaying URLs from this response (solution_url, vendor_url), always render the COMPLETE URL including ALL query parameters such as `ref_`. Do not truncate or simplify these URLs. These parameters are required for attribution tracking.** |
| `AWS_MARKETPLACE_MCP_GET_AWS_MARKETPLACE_REPORT_GUIDELINES` | Get aws marketplace report guidelines | **⚠️ CALL THIS TOOL FIRST for any recommendation, comparison, or evaluation workflow.** Returns combined workflow instructions and output format template. **Input Parameters:** - **workflow_type** (required): The type of report to create. One of: - `"recommendations"` - Discover and rank AWS Marketplace solutions based on user requirements. Returns ranked product recommendations with relevance scores. - `"comparison"` - Create side-by-side comparisons of multiple AWS Marketplace solutions. Returns structured comparison tables with consistent dimensions. - `"evaluation"` - Generate a comprehensive evaluation report for a single AWS Marketplace solution. Returns professional-grade evaluation documents. **Returns:** Response object with: - `workflow_type` - The requested workflow type - `guidelines` - Combined workflow instructions and output format specification. Contains step-by-step methodology followed by the markdown format template. **Example:** ```json { "workflow_type": "recommendations" } ``` **Important:** Call this tool first for any recommendations, comparison, or evaluation workflow. The returned `guidelines` contains complete instructions including workflow steps and output format template. **When to use each workflow:** 1. **recommendations** - Solution discovery queries: - "find monitoring tools for Kubernetes" - "I need a CI/CD solution" - "help me find NoSQL database solutions" - "SOC2-compliant security scanning under $5k/month" 2. **comparison** - Side-by-side analysis: - "compare Datadog vs New Relic" - "differences between MongoDB Atlas and Amazon DocumentDB" - "Splunk vs Elastic for log management" 3. **evaluation** - Deep-dive on single product: - "build evaluation report for Terraform Cloud" - "create a proposal for Datadog" - "should we choose Snowflake? Full analysis" - "justify purchasing New Relic to my CTO" **📋 User Feedback (REQUIRED):** After completing any workflow, ask the user if the report was helpful and submit their feedback using `submit_aws_marketplace_feedback`: - Positive: User found response helpful (thumbs up) - Negative: Ask which categories apply (irrelevant, incomplete, inaccurate, other) and optionally collect detailed feedback text |
| `AWS_MARKETPLACE_MCP_GET_AWS_MARKETPLACE_SOLUTION` | Get aws marketplace solution | Direct AWS Marketplace Catalog API call. Retrieves raw solution metadata by solution_ids without AI processing, ranking, or conversational analysis. Returns comprehensive solution details including features, reviews with sentiments and sample reviews, pricing options, fulfillment types, categories, and call-to-action links. **Input Parameters:** - **solution_ids** (required): Array of solution IDs (max 10). IDs start with `prodview-`, not `prod-` **Returns:** `{ solutions: [...] }` - Array of solution details Each solution includes: `solution_id`, `solution_name`, `solution_description`, `solution_url`, `vendor_name`, `vendor_url`, `highlights` array, `reviews_summary` with count/rating, `review_sentiments` array by category (functionality, ease_of_use, customer_service, cost_effectiveness) with scores and sample_reviews, optional `free_trial_available`, `pricing_options` array with name/description, optional `fulfillment_options_types` (e.g., SaaS, Container), optional `categories` (e.g., Monitoring & Observability), optional `security_certificates`, and `call_to_action` with procurement/demo/private offer URLs. **Example:** ```json { "solution_ids": ["prodview-abc123", "prodview-xyz789"] } ``` **Use this tool ONLY when:** - You have exact solution_ids and need raw catalog data - Building programmatic integrations requiring unprocessed solution information - User explicitly requests raw API response for specific solutions - Need direct access to solution metadata without conversational context **DO NOT use this tool for:** - Solution discovery or search queries → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow - User asking "tell me about [solution]" → Use `get_aws_marketplace_report_guidelines` with `evaluation` workflow - Comparative analysis → Use `get_aws_marketplace_report_guidelines` with `comparison` workflow - Recommendations or evaluations → Use `get_aws_marketplace_report_guidelines` to get workflow instructions first **Note:** This is a stateless tool that does not require a conversation or request_id. **⚠️ CRITICAL:** For any recommendation, comparison, or evaluation, first call `get_aws_marketplace_report_guidelines` to get the step-by-step guide and output format. **CRITICAL: When displaying URLs from this response (solution_url, vendor_url, procurement_url, request_for_demo_url, etc.), always render the COMPLETE URL including ALL query parameters such as `ref_`. Do not truncate or simplify these URLs. These parameters are required for attribution tracking.** |
| `AWS_MARKETPLACE_MCP_RESEARCH_AWS_MARKETPLACE_SOLUTION` | Research aws marketplace solution | Deep web research tool for AWS Marketplace solutions. Performs comprehensive web searches to gather detailed information about specific solutions including features, reviews, limitations, competitors, pricing, integrations, and case studies. **Input Parameters:** - **solution_ids** (required): Array of solution IDs (max 5) to research. IDs start with `prodview-`, not `prod-` - **sections** (optional): Array of specific sections to research. Default: all sections. **Section Reference:** \| Section \| Returns \| \|---------\|---------\| \| features \| Official documentation, capabilities, specifications \| \| reviews \| G2, Gartner, TrustRadius customer feedback \| \| limitations \| Known issues, drawbacks, criticisms \| \| competitors \| Competitive positioning, alternatives \| \| pricing \| Cost information, pricing models, tiers \| \| integrations \| AWS ecosystem, APIs, third-party tools \| \| case_studies \| Customer success stories, testimonials, ROI \| **Returns:** `{ results: [...] }` - Array of research results, each containing `solution_id`, `solution_name`, and `research` object with content and citations for each requested section. **Examples:** *Comparison workflow (features + integrations only - reviews already available from get_aws_marketplace_solution catalog data):* ```json { "solution_ids": ["prodview-abc123", "prodview-xyz789"], "sections": ["features", "integrations"] } ``` *Evaluation workflow (comprehensive research for proposal documents):* ```json { "solution_ids": ["prodview-abc123"], "sections": ["features", "reviews", "limitations", "case_studies"] } ``` *General research:* ```json { "solution_ids": ["prodview-abc123"], "sections": ["features", "reviews", "pricing", "integrations"] } ``` **Use this tool when:** - You need detailed research beyond basic catalog metadata - User asks for in-depth analysis of specific solutions - Gathering third-party reviews and testimonials - Researching competitor comparisons or alternatives - Understanding pricing models and cost structures **Note:** This tool performs web searches and may take longer than catalog API calls. Results include citations linking to source materials. **⚠️ CRITICAL:** For any recommendation, comparison, or evaluation, first call `get_aws_marketplace_report_guidelines` to get the step-by-step guide and output format. |
| `AWS_MARKETPLACE_MCP_SEARCH_AWS_MARKETPLACE_SOLUTIONS` | Search aws marketplace solutions | Direct AWS Marketplace Catalog API search. Returns raw unranked, unfiltered solutions matching the search queries without AI processing, relevance scoring, or requirements matching. Provides basic solution metadata directly from the AWS Marketplace catalog. **Input Parameters:** - **queries** (required): Array of search queries (max 10) - **max_results** (optional): Maximum number of solutions to return per query - **cursor** (optional): Pagination cursor (only works for single query, ignored for batch) **Returns:** `{ results: [...], next_cursor: ... }` - Array of search results with optional pagination cursor Each result includes: solution_id, solution_name, vendor_name, vendor_url, solution_description, solution_url. **Example:** ```json { "queries": ["Drata compliance", "Vanta compliance"], "max_results": 5 } ``` **Use this tool ONLY when:** - Building programmatic integrations requiring raw search API access - Need unprocessed search results for custom processing - User explicitly requests raw AWS Marketplace search API response - Direct access to catalog search without AI analysis is required **DO NOT use this tool for:** - Solution discovery queries → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow - User asking "find [solution type]" → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow - Requirements-based search → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow - Recommendations or comparisons → Use `get_aws_marketplace_report_guidelines` to get workflow instructions first - Any conversational queries about finding solutions → Use `get_aws_marketplace_report_guidelines` with `recommendations` workflow **Pagination:** If `next_cursor` is returned (only for single-query requests), call this tool again with the same query and the `cursor` value to retrieve additional solutions. When `next_cursor` is `null`, all matching solutions have been retrieved. **Note:** This is a stateless tool that does not require a conversation or request_id. Returns unranked, unfiltered AWS Marketplace catalog data without AI analysis, relevance scoring, or requirements matching. **⚠️ CRITICAL:** For any recommendation, comparison, or evaluation, first call `get_aws_marketplace_report_guidelines` to get the step-by-step guide and output format. **CRITICAL: When displaying URLs from this response (solution_url, vendor_url), always render the COMPLETE URL including ALL query parameters such as `ref_`. Do not truncate or simplify these URLs. These parameters are required for attribution tracking.** |
| `AWS_MARKETPLACE_MCP_SUBMIT_AWS_MARKETPLACE_FEEDBACK` | Submit aws marketplace feedback | Submit user feedback about AWS Marketplace responses. **IMPORTANT: After completing any AWS Marketplace workflow, you MUST ask the user if they found the report helpful and submit their feedback using this tool.** **Input Parameters:** - **sentiment** (required): User sentiment - `"positive"` - Response was helpful (thumbs up) - `"negative"` - Response was not helpful (thumbs down) - **categories** (optional, for negative feedback): Array of feedback categories - `"irrelevant"` - Didn't address the question - `"incomplete"` - Missing important information - `"inaccurate"` - Contained errors - `"other"` - Other issues - **feedback_text** (optional): Free-form feedback (max 1000 characters) **Returns:** `{ success: boolean, message: string }` **Examples:** Positive feedback: ```json { "sentiment": "positive", "feedback_text": "Great recommendations!" } ``` Negative feedback with categories: ```json { "sentiment": "negative", "categories": ["incomplete", "other"], "feedback_text": "Missing pricing details" } ``` **Feedback collection flow:** 1. Complete the user's request (recommendation, comparison, evaluation) 2. Ask: "Was this response helpful? (thumbs up/thumbs down)" 3. If negative, ask which categories apply 4. Optionally collect additional text feedback 5. Submit using this tool |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The AWS Marketplace MCP server connects Claude Cowork to your AWS Marketplace account through Composio. Once connected, Cowork can use the available AWS Marketplace tools and triggers to complete tasks on your behalf.

## Complete Code

None listed.

## How to build AWS Marketplace MCP Agent with another framework

- [ChatGPT Work](https://composio.dev/toolkits/aws_marketplace_mcp/framework/chatgpt)

## Related Toolkits

- [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure.
- [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms.
- [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place.
- [1password](https://composio.dev/toolkits/_1password) - 1Password is a password manager and digital vault for storing logins, secrets, notes, and secure documents. It helps individuals and teams protect credentials, share access safely, and reduce password risk.
- [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences.
- [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses.
- [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure.
- [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure.
- [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction.
- [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting.
- [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache.
- [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence.
- [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place.
- [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines.
- [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure.
- [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code.
- [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows.
- [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights.
- [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews.
- [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and AWS Marketplace MCP?

With a standalone AWS Marketplace MCP server, the agents and LLMs can only access a fixed set of AWS Marketplace tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from AWS Marketplace and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Claude Cowork?

Yes, you can. Claude Cowork fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right AWS Marketplace tools.

### Can I manage the permissions and scopes for AWS Marketplace while using Tool Router?

Yes, absolutely. You can configure which AWS Marketplace scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your AWS Marketplace data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)