6sense
Ask an AI agent about 6sense account insights, buying signals and keyword trends.
Search and evaluate third-party software listed on AWS Marketplace from an AI agent.
Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.
Paste it into any MCP client. Setup docs
The AWS Marketplace MCP server lets Claude, ChatGPT and other agents search the AWS Marketplace catalogue of third-party software and assemble comparison or evaluation reports. Its six tools search listings, fetch listing metadata, find related products, run web research and submit feedback. No sign-in is needed. Five tools only read; the sixth writes to AWS.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
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.**
**⚠️ 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
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.**
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.
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.**
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
Read from the server on 2026-08-18, including each tool's own safety annotations.
call_to_action block returns procurement, demo, private-offer and free-trial URLs for a human to follow. Despite the directory description mentioning requesting private offers, the connector surfaces the link rather than making the request.queries, solution_ids, max_results, cursor, sections, workflow_type, sentiment, categories and feedback_text. There is no account ID, no region parameter, no resource identifier and no credential field anywhere. This connector cannot see your infrastructure, your bill or your existing subscriptions.research_aws_marketplace_solution sources pricing from the open web, which can be out of date.research_aws_marketplace_solution is the only openWorldHint: true tool and runs live web searches. Its findings carry citations and should be read as web research, not catalogue fact.isError: true rather than as JSON-RPC errors. A client checking only the HTTP status or the error field will read a failed search as an empty one.APIReference path that 301s to the developerguide path; the destination is the page cited here.initialize, tools/list, and two unauthenticated calls to read-only tools. submit_aws_marketplace_feedback was never called and no feedback was submitted to AWS. Every claim about it comes from its schema, its description and AWS's documentation.No. AWS documents the server as requiring no authentication and tells clients to omit auth headers. We confirmed this on 2026-08-18 by running a search anonymously against the live endpoint, which returned real catalogue results with no credential. Anthropic's directory records the connector as auth_required, which does not match what the server actually does.
Three fields and nothing else: a required sentiment of positive or negative, optional categories from a fixed list, and up to 1000 characters of free text. The schema carries no account identifier and no conversation content. It writes a rating of the report into AWS Marketplace's own feedback dataset, which is why it is the one tool not marked read-only.
They take different inputs and hit different systems. search_aws_marketplace_solutions takes keyword queries and returns matching listings. get_aws_marketplace_solution takes listing IDs and returns full catalogue metadata for them. research_aws_marketplace_solution also takes listing IDs, but runs live web searches against sources outside AWS and returns cited findings.
No. It queries a commercial catalogue of third-party listings from sellers who register with AWS. AWS describes it as a curated digital catalog, not an independent evaluation. Any ranking or top pick you see is produced by the model from the format template the server supplies, not by an assessment AWS or Agentman performed.
Because it is an orchestration tool. AWS calls it the entry point for report workflows, and it returns a step-by-step method plus an exact markdown template the model is told to follow. We read all three workflows on 2026-08-18. It shapes how the assistant writes, which no other tool on this server does.
Yes. Every listing and seller URL we received on 2026-08-18 carried ref_=MAX_MCP plus src, rid and sid parameters. The tool descriptions instruct the model to render these URLs complete and never truncate them, and AWS states the parameters are required for attribution tracking of which workflow generated a click.
The listing is stale and describes a different design. Only three names appear in both. The directory's other eight imply a stateful conversational server with file uploads and saved conversations. The live server is stateless, per AWS documentation, and replaces those with a guidelines tool, a web-research tool and a feedback tool. The handshake is authoritative.
APIReference path that returns 301 to this developerguide path. Source for the endpoint, the streamable-HTTP and JSON-RPC transport, the statement that no authentication is required and auth headers should be omitted, the six-tool table with its read-only column, the stateless design, the Mcp-Session-Id diagnostics-and-analytics framing, the protocol-version header, the per-tool input and output field tables, the batch and pagination limits, the research tool's visibility rule for clients with native web search, the example prompts and use cases, the connector setup steps, and the three error categories including isError: true inside a result. · retrieved 2026-08-18https://marketplace-mcp.us-east-1.api.aws/mcp (2026-08-18). Anonymous initialize returned HTTP 200 with serverInfo "AWS Marketplace - Agent mode" 1.0.0; anonymous tools/list returned 6 tools with full schemas and annotations; anonymous calls to get_aws_marketplace_report_guidelines (all three workflow_type values) and search_aws_marketplace_solutions returned HTTP 200 with real content and no auth challenge. Source for the verified auth posture, the annotation split, the guidelines text including the format templates and the feedback requirement, and the observed ref_=MAX_MCP tracking parameters. submit_aws_marketplace_feedback was never called. · retrieved 2026-08-18marketplace-mcp.us-east-1.api.aws resolves; us-west-2, us-east-2, eu-west-1 and ap-southeast-1 return NXDOMAIN. Source for the single-endpoint finding. · retrieved 2026-08-18works_with list, the support address, and the 11 listed tool names that the live handshake contradicts. Anthropic's directory documentation states that verification is not a security audit and reflects the level of review a connector received. · retrieved 2026-08-16robots.txt policy check (2026-08-18). docs.aws.amazon.com/robots.txt returns HTTP 200 and disallows only dated legacy API paths, not the marketplace developer guide; aws.amazon.com/robots.txt returns HTTP 200 and disallows marketplace search and review-writing paths, neither of which was fetched. No Content-Signal directive is present on either host, and no named AI crawler is singled out. docs.aws.amazon.com/llms.txt returns HTTP 200; aws.amazon.com/llms.txt returns 404. · retrieved 2026-08-18Connect AWS Marketplace once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.