{"format":"verfy.mcp-server/1","page":"https://verfy.dev/servers/aws-documentation","collectedAt":"2026-11-13","server":{"id":"aws-documentation","eco":"pypi","pkg":"awslabs.aws-documentation-mcp-server","releases":[{"version":"1.1.29","published":"2026-08-05","started":true},{"version":"1.1.30","published":"2026-08-10","started":true},{"version":"1.2.0","published":"2026-08-26","started":true},{"version":"1.2.1","published":"2026-09-08","started":true},{"version":"1.2.2","published":"2026-09-30","started":true},{"version":"1.2.3","published":"2026-10-13","started":true},{"version":"1.2.4","published":"2026-10-30","started":true},{"version":"1.2.5","published":"2026-11-09","started":true}],"tools":[{"name":"read_documentation","pin":"sha256:1f833a30861a9895404ee4f70bdd5583433263413bb8cd98044a2962e022e4a6","description":"Fetch and convert an AWS documentation page to markdown format.\n\n## Usage\n\nThis tool retrieves the content of an AWS documentation page and converts it to markdown format.\nFor long documents, you can make multiple calls with different start_index values to retrieve\nthe entire content in chunks.\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html or .md\n\n## Example URLs\n\n- https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html\n- https://docs.aws.amazon.com/lambda/latest/dg/lambda-invocation.html\n\n## Output Format\n\nThe output is formatted as markdown text with:\n- Preserved headings and structure\n- Code blocks for examples\n- Lists and tables converted to markdown format\n- Links to other pages kept as published, often relative (e.g. `invocation-sync.md`);\n  resolve a relative link against the page URL before reading it\n\n## Large Tables\n\nTables with more than 20 rows are automatically truncated to show only the header and 5 sample rows,\nalong with a hint to use the `search_table` tool. Use `search_table` to filter and retrieve specific\nrows from large tables (e.g., service quotas, IAM actions).\n\n## Handling Long Documents\n\nIf the response indicates the document was truncated, you have several options:\n\n1. **Continue Reading**: Make another call with start_index set to the end of the previous response\n2. **Stop Early**: For very long documents (>30,000 characters), if you've already found the specific information needed, you can stop reading\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to read\n    max_length: Maximum number of characters to return\n    start_index: On return output starting at this character index\n\nReturns:\n    Markdown content of the AWS documentation\n"},{"name":"read_sections","pin":"sha256:f469d4abb5cdcd1d9bc5866428393a4821b39552f124747aae40d6af0e211e00","description":"Extract specific sections from AWS documentation pages by title.\n\nRetrieves a page, converts to markdown, and returns only matching sections.\nSection matching is case-insensitive and handles whitespace differences.\n\nA title can be a heading at any level. Each section runs to the next heading at the same or\na higher level, so it includes its subsections. A title that names only the page returns\nthe whole page, paginated like read_documentation; if the page title is also a section\nheading, those sections are returned instead.\n\n## URL Requirements\n- Must end with .html or .md\n\n## Large Tables\n\nTables with more than 20 rows are automatically truncated to show only the header and 5 sample rows,\nalong with a hint to use the `search_table` tool. Use `search_table` to filter and retrieve specific\nrows from large tables (e.g., service quotas, IAM actions).\n\n## Read Sections Tips\n\n- Use exact section titles from search results 'sections' field when available\n- Section matching is case-insensitive and handles whitespace differences\n- Include multiple related sections in one call for comprehensive coverage\n- Links to other pages are kept as published, often relative (e.g. `invocation-sync.md`);\n  resolve a relative link against the page URL before reading it\n\n## Example Usage\n\n```\n# If query is about S3 bucket naming rules:\n# Available sections: ['General purpose buckets naming rules', 'Example general purpose bucket names', 'Best practices', 'Creating a bucket that uses a GUID in the bucket name']\n# Read these specific sections:\nread_sections(\n    url='https://docs.aws.amazon.com/s3/latest/userguide/bucketnamingrules.html',\n    section_titles=['General purpose buckets naming rules', 'Best practices'],\n)\n\n# If query is about Python Lambda function examples:\n# Available sections: ['Example Python Lambda function code', 'Handler naming conventions', 'Using the Lambda event object', 'Accessing and using the Lambda context object'. 'Valid handler signatures for Python handlers', 'Returning a value', 'Using the AWS SDK for Python (Boto3) in your handler', 'Accessing environment variables, 'Code best practices for Python Lambda functions']\n# Read these specific sections:\nread_sections(\n    url='https://docs.aws.amazon.com/lambda/latest/dg/python-handler.html',\n    section_titles=[\n        'Example Python Lambda function code',\n        'Code best practices for Python Lambda functions',\n    ],\n)\n```\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to read\n    section_titles: List of section titles to extract\n\nReturns:\n    Filtered markdown content containing only the requested sections\n"},{"name":"search_table","pin":"sha256:c2369f6b54807705cfff309f5840c6d303fd1246dd6481c208981415cc726790","description":"Search for specific rows in a large documentation table.\n\nUse this tool when you need specific rows from a large documentation table\n(e.g., service quotas, pricing tables, supported models lists). Returns\nmatching rows as JSON instead of dumping the entire table.\n\nThis is more efficient than read_sections for pages with hundreds of table rows.\nIf read_sections or read_documentation indicates a table was truncated, use this\ntool to find the specific rows you need.\n\n## Section Title\n\n- If you know the exact section title, provide it for precision\n- If unsure, omit section_title — the tool will search all tables on the page\n- Use section titles from search_documentation results (TOC) or read_documentation output\n- If the section title is wrong, the hint field will list available sections\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html or .md\n\n## Example Usage\n\n```\n# With section title (searches all tables in that section):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    section_title='Amazon Bedrock service quotas',\n    query='Titan Text Embeddings V2',\n)\n\n# Without section title (searches all tables on the page):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    query='Claude 3 Sonnet requests',\n)\n```\n\n## Response Format\n\nReturns a SearchTableResponse with:\n- tables_searched: Number of tables searched\n- tables_with_matches: Number of tables containing matching rows\n- hint: Guidance message when no matches found, section not found, or no tables on page\n- results: Array of table result objects, each with:\n    - table_heading: The sub-heading above the table (if any)\n    - columns: Column headers for that table\n    - parent_columns: (optional) For rowspan/nested tables, which columns are group headers\n    - child_columns: (optional) For rowspan/nested tables, which columns are nested under groups\n    - total_rows: Total rows (or groups, for nested tables) in that table\n    - matched_rows: Number of rows/groups matching the query per table\n    - showing: Number of rows/groups returned per table (capped by max_rows per table)\n    - rows: Array of matching row objects. For flat tables: {column → value}.\n      For nested tables: {parent_col → value, ..., \"rows\": [{child_col → value}, ...]}\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: AWS documentation page URL (must end with .html or .md)\n    section_title: The section heading containing the table (optional — omit to search all tables on the page)\n    query: Search term to filter rows (all words must match, case-insensitive)\n    max_rows: Maximum matching rows to return per table (default 20)\n\nReturns:\n    SearchTableResponse with matching rows grouped by table\n"},{"name":"search_documentation","pin":"sha256:47749331b9ce4e9455ba8dc4ae160af35afc3a5372bf034571b0f3487ffe5ccc","description":"Search AWS documentation using the official AWS Documentation Search API.\n\n## Usage\n\nThis tool searches across all AWS documentation for pages matching your search phrase.\nUse it to find relevant documentation when you don't have a specific URL.\n\n## Search Tips\n\n- Use specific technical terms rather than general phrases\n- Include service names to narrow results (e.g., \"S3 bucket versioning\" instead of just \"versioning\")\n- Use quotes for exact phrase matching (e.g., \"AWS Lambda function URLs\")\n- Include abbreviations and alternative terms to improve results\n- Use guide_type and product_type filters found from a SearchResponse's \"facets\" property:\n    - Filter only for broad search queries with patterns:\n        - \"What is [service]?\" -> product_types: [\"Amazon Simple Storage Service\"]\n        - \"How to use <service 1> with <service 2>?\" -> product_types: [<service 1>, <service 2>]\n        - \"[service] getting started\" -> product_types: [<service>] + guide_types: [\"User Guide, \"Developer Guide\"]\n        - \"API reference for [service]\" -> product_types: [<service>] + guide_types: [\"API Reference\"]\n\n## Result Interpretation\n\nEach SearchResponse includes:\n- search_results: List of documentation pages, each with:\n    - rank_order: The relevance ranking (lower is more relevant)\n    - url: The documentation page URL\n    - title: The page title\n    - context: A brief excerpt or summary (if available)\n    - recommended_sections: A subset of section titles ranked as most relevant to the query, in rank order (when available) - Pass these directly to read_sections for targeted content extraction\n    - sections: All available section titles for this page (when available) - individual titles can be used with the read_sections tool for targeted content extraction\n    - metadata: Optional per-result context (when available). May include:\n        - additional_urls: Other doc URLs related to the same result `{url, section_title, section_anchor}` - pass `section_title` to read_sections to fetch content; use `url#section_anchor` when citing\n- facets: Available filters (product_types, guide_types) for refining searches\n- query_id: Unique identifier for this search session\n- metadata: Optional response-level context (when available). May include:\n    - discovered_services: AWS services inferred from the query that may be relevant beyond the top results\n    - related_tasks: Related operations or workflows the user may want to follow up on, each with its own doc URLs\n    - relationships: Named connections between information in the search results, useful for understanding how the returned topics relate to each other\n\n\nArgs:\n    ctx: MCP context for logging and error handling\n    search_phrase: Search phrase to use\n    search_intent: The intent behind the search requested by the user\n    limit: Maximum number of results to return\n    product_types: Filter by AWS product/service\n    guide_types: Filter by guide type\n\nReturns:\n    List of search results with URLs, titles, query ID, context snippets, and facets for filtering\n"},{"name":"recommend","pin":"sha256:f4b4bf33bec4bc63cea3a83bdd36dd99fccb4c29e8078d55b05087a446ff5b4a","description":"Get content recommendations for an AWS documentation page.\n\n## Usage\n\nThis tool provides recommendations for related AWS documentation pages based on a given URL.\nUse it to discover additional relevant content that might not appear in search results.\n\n## Recommendation Types\n\nThe recommendations include three categories:\n\n1. **New**: Recently added pages within the same AWS service - useful for finding newly released features\n2. **Similar**: Pages covering similar topics to the current page\n3. **Journey**: Pages commonly viewed next by other users\n\n## When to Use\n\n- After reading a documentation page to find related content\n- When exploring a new AWS service to discover important pages\n- To find alternative explanations of complex concepts\n- To find newly released information by using a service's welcome page URL and checking the **New** recommendations\n\n## Finding New Features\n\nTo find newly released information about a service:\n1. Find any page belong to that service, typically you can try the welcome page\n2. Call this tool with that URL\n3. Look specifically at the **New** recommendation type in the results\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- A .md page URL, such as a link followed from read_documentation output, is looked up as its .html page\n\n## Result Interpretation\n\nEach recommendation includes:\n- url: The documentation page URL\n- title: The page title\n- context: A brief description (if available)\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to get recommendations for\n\nReturns:\n    List of recommended pages with URLs, titles, and context\n"}],"updates":[{"from":"1.1.29","to":"1.1.30","published":"2026-08-10","bump":"patch","added":[],"removed":[],"changed":[]},{"from":"1.1.30","to":"1.2.0","published":"2026-08-26","bump":"minor","added":[],"removed":[],"changed":[{"tool":"recommend","description":true,"schema":false,"before":"Get content recommendations for an AWS documentation page.\n\n## Usage\n\nThis tool provides recommendations for related AWS documentation pages based on a given URL.\nUse it to discover additional relevant content that might not appear in search results.\n\n## Recommendation Types\n\nThe recommendations include four categories:\n\n1. **Highly Rated**: Popular pages within the same AWS service\n2. **New**: Recently added pages within the same AWS service - useful for finding newly released features\n3. **Similar**: Pages covering similar topics to the current page\n4. **Journey**: Pages commonly viewed next by other users\n\n## When to Use\n\n- After reading a documentation page to find related content\n- When exploring a new AWS service to discover important pages\n- To find alternative explanations of complex concepts\n- To discover the most popular pages for a service\n- To find newly released information by using a service's welcome page URL and checking the **New** recommendations\n\n## Finding New Features\n\nTo find newly released information about a service:\n1. Find any page belong to that service, typically you can try the welcome page\n2. Call this tool with that URL\n3. Look specifically at the **New** recommendation type in the results\n\n## Result Interpretation\n\nEach recommendation includes:\n- url: The documentation page URL\n- title: The page title\n- context: A brief description (if available)\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to get recommendations for\n\nReturns:\n    List of recommended pages with URLs, titles, and context\n","after":"Get content recommendations for an AWS documentation page.\n\n## Usage\n\nThis tool provides recommendations for related AWS documentation pages based on a given URL.\nUse it to discover additional relevant content that might not appear in search results.\n\n## Recommendation Types\n\nThe recommendations include three categories:\n\n1. **New**: Recently added pages within the same AWS service - useful for finding newly released features\n2. **Similar**: Pages covering similar topics to the current page\n3. **Journey**: Pages commonly viewed next by other users\n\n## When to Use\n\n- After reading a documentation page to find related content\n- When exploring a new AWS service to discover important pages\n- To find alternative explanations of complex concepts\n- To find newly released information by using a service's welcome page URL and checking the **New** recommendations\n\n## Finding New Features\n\nTo find newly released information about a service:\n1. Find any page belong to that service, typically you can try the welcome page\n2. Call this tool with that URL\n3. Look specifically at the **New** recommendation type in the results\n\n## Result Interpretation\n\nEach recommendation includes:\n- url: The documentation page URL\n- title: The page title\n- context: A brief description (if available)\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to get recommendations for\n\nReturns:\n    List of recommended pages with URLs, titles, and context\n"}]},{"from":"1.2.0","to":"1.2.1","published":"2026-09-08","bump":"patch","added":[],"removed":[],"changed":[]},{"from":"1.2.1","to":"1.2.2","published":"2026-09-30","bump":"patch","added":[],"removed":[],"changed":[{"tool":"search_table","description":true,"schema":false,"before":"Search for specific rows in a large documentation table.\n\nUse this tool when you need specific rows from a large documentation table\n(e.g., service quotas, pricing tables, supported models lists). Returns\nmatching rows as JSON instead of dumping the entire table.\n\nThis is more efficient than read_sections for pages with hundreds of table rows.\nIf read_sections or read_documentation indicates a table was truncated, use this\ntool to find the specific rows you need.\n\n## Section Title\n\n- If you know the exact section title, provide it for precision\n- If unsure, omit section_title — the tool will search all tables on the page\n- Use section titles from search_documentation results (TOC) or read_documentation output\n- If the section title is wrong, the hint field will list available sections\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html\n\n## Example Usage\n\n```\n# With section title (searches all tables in that section):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    section_title='Amazon Bedrock service quotas',\n    query='Titan Text Embeddings V2',\n)\n\n# Without section title (searches all tables on the page):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    query='Claude 3 Sonnet requests',\n)\n```\n\n## Response Format\n\nReturns a SearchTableResponse with:\n- tables_searched: Number of tables searched\n- tables_with_matches: Number of tables containing matching rows\n- hint: Guidance message when no matches found, section not found, or no tables on page\n- error: Error message on HTTP/transport failures only\n- results: Array of table result objects, each with:\n    - table_heading: The sub-heading above the table (if any)\n    - columns: Column headers for that table\n    - parent_columns: (optional) For rowspan/nested tables, which columns are group headers\n    - child_columns: (optional) For rowspan/nested tables, which columns are nested under groups\n    - total_rows: Total rows (or groups, for nested tables) in that table\n    - matched_rows: Number of rows/groups matching the query per table\n    - showing: Number of rows/groups returned per table (capped by max_rows per table)\n    - rows: Array of matching row objects. For flat tables: {column → value}.\n      For nested tables: {parent_col → value, ..., \"rows\": [{child_col → value}, ...]}\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: AWS documentation page URL (must end with .html)\n    section_title: The section heading containing the table (optional — omit to search all tables on the page)\n    query: Search term to filter rows (all words must match, case-insensitive)\n    max_rows: Maximum matching rows to return per table (default 20)\n\nReturns:\n    SearchTableResponse with matching rows grouped by table\n","after":"Search for specific rows in a large documentation table.\n\nUse this tool when you need specific rows from a large documentation table\n(e.g., service quotas, pricing tables, supported models lists). Returns\nmatching rows as JSON instead of dumping the entire table.\n\nThis is more efficient than read_sections for pages with hundreds of table rows.\nIf read_sections or read_documentation indicates a table was truncated, use this\ntool to find the specific rows you need.\n\n## Section Title\n\n- If you know the exact section title, provide it for precision\n- If unsure, omit section_title — the tool will search all tables on the page\n- Use section titles from search_documentation results (TOC) or read_documentation output\n- If the section title is wrong, the hint field will list available sections\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html\n\n## Example Usage\n\n```\n# With section title (searches all tables in that section):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    section_title='Amazon Bedrock service quotas',\n    query='Titan Text Embeddings V2',\n)\n\n# Without section title (searches all tables on the page):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    query='Claude 3 Sonnet requests',\n)\n```\n\n## Response Format\n\nReturns a SearchTableResponse with:\n- tables_searched: Number of tables searched\n- tables_with_matches: Number of tables containing matching rows\n- hint: Guidance message when no matches found, section not found, or no tables on page\n- results: Array of table result objects, each with:\n    - table_heading: The sub-heading above the table (if any)\n    - columns: Column headers for that table\n    - parent_columns: (optional) For rowspan/nested tables, which columns are group headers\n    - child_columns: (optional) For rowspan/nested tables, which columns are nested under groups\n    - total_rows: Total rows (or groups, for nested tables) in that table\n    - matched_rows: Number of rows/groups matching the query per table\n    - showing: Number of rows/groups returned per table (capped by max_rows per table)\n    - rows: Array of matching row objects. For flat tables: {column → value}.\n      For nested tables: {parent_col → value, ..., \"rows\": [{child_col → value}, ...]}\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: AWS documentation page URL (must end with .html)\n    section_title: The section heading containing the table (optional — omit to search all tables on the page)\n    query: Search term to filter rows (all words must match, case-insensitive)\n    max_rows: Maximum matching rows to return per table (default 20)\n\nReturns:\n    SearchTableResponse with matching rows grouped by table\n"}]},{"from":"1.2.2","to":"1.2.3","published":"2026-10-13","bump":"patch","added":[],"removed":[],"changed":[]},{"from":"1.2.3","to":"1.2.4","published":"2026-10-30","bump":"patch","added":[],"removed":[],"changed":[]},{"from":"1.2.4","to":"1.2.5","published":"2026-11-09","bump":"patch","added":[],"removed":[],"changed":[{"tool":"read_documentation","description":true,"schema":false,"before":"Fetch and convert an AWS documentation page to markdown format.\n\n## Usage\n\nThis tool retrieves the content of an AWS documentation page and converts it to markdown format.\nFor long documents, you can make multiple calls with different start_index values to retrieve\nthe entire content in chunks.\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html\n\n## Example URLs\n\n- https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html\n- https://docs.aws.amazon.com/lambda/latest/dg/lambda-invocation.html\n\n## Output Format\n\nThe output is formatted as markdown text with:\n- Preserved headings and structure\n- Code blocks for examples\n- Lists and tables converted to markdown format\n\n## Large Tables\n\nTables with more than 20 rows are automatically truncated to show only the header and 5 sample rows,\nalong with a hint to use the `search_table` tool. Use `search_table` to filter and retrieve specific\nrows from large tables (e.g., service quotas, IAM actions).\n\n## Handling Long Documents\n\nIf the response indicates the document was truncated, you have several options:\n\n1. **Continue Reading**: Make another call with start_index set to the end of the previous response\n2. **Stop Early**: For very long documents (>30,000 characters), if you've already found the specific information needed, you can stop reading\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to read\n    max_length: Maximum number of characters to return\n    start_index: On return output starting at this character index\n\nReturns:\n    Markdown content of the AWS documentation\n","after":"Fetch and convert an AWS documentation page to markdown format.\n\n## Usage\n\nThis tool retrieves the content of an AWS documentation page and converts it to markdown format.\nFor long documents, you can make multiple calls with different start_index values to retrieve\nthe entire content in chunks.\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html or .md\n\n## Example URLs\n\n- https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html\n- https://docs.aws.amazon.com/lambda/latest/dg/lambda-invocation.html\n\n## Output Format\n\nThe output is formatted as markdown text with:\n- Preserved headings and structure\n- Code blocks for examples\n- Lists and tables converted to markdown format\n- Links to other pages kept as published, often relative (e.g. `invocation-sync.md`);\n  resolve a relative link against the page URL before reading it\n\n## Large Tables\n\nTables with more than 20 rows are automatically truncated to show only the header and 5 sample rows,\nalong with a hint to use the `search_table` tool. Use `search_table` to filter and retrieve specific\nrows from large tables (e.g., service quotas, IAM actions).\n\n## Handling Long Documents\n\nIf the response indicates the document was truncated, you have several options:\n\n1. **Continue Reading**: Make another call with start_index set to the end of the previous response\n2. **Stop Early**: For very long documents (>30,000 characters), if you've already found the specific information needed, you can stop reading\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to read\n    max_length: Maximum number of characters to return\n    start_index: On return output starting at this character index\n\nReturns:\n    Markdown content of the AWS documentation\n"},{"tool":"read_sections","description":true,"schema":false,"before":"Extract specific sections from AWS documentation pages by title.\n\nRetrieves a page, converts to markdown, and returns only matching sections.\nSection matching is case-insensitive and handles whitespace differences.\n\n## URL Requirements\n- Must end with .html\n\n## Large Tables\n\nTables with more than 20 rows are automatically truncated to show only the header and 5 sample rows,\nalong with a hint to use the `search_table` tool. Use `search_table` to filter and retrieve specific\nrows from large tables (e.g., service quotas, IAM actions).\n\n## Read Sections Tips\n\n- Use exact section titles from search results 'sections' field when available\n- Section matching is case-insensitive and handles whitespace differences\n- Include multiple related sections in one call for comprehensive coverage\n\n## Example Usage\n\n```\n# If query is about S3 bucket naming rules:\n# Available sections: ['General purpose buckets naming rules', 'Example general purpose bucket names', 'Best practices', 'Creating a bucket that uses a GUID in the bucket name']\n# Read these specific sections:\nread_sections(\n    url='https://docs.aws.amazon.com/s3/latest/userguide/bucketnamingrules.html',\n    section_titles=['General purpose buckets naming rules', 'Best practices'],\n)\n\n# If query is about Python Lambda function examples:\n# Available sections: ['Example Python Lambda function code', 'Handler naming conventions', 'Using the Lambda event object', 'Accessing and using the Lambda context object'. 'Valid handler signatures for Python handlers', 'Returning a value', 'Using the AWS SDK for Python (Boto3) in your handler', 'Accessing environment variables, 'Code best practices for Python Lambda functions']\n# Read these specific sections:\nread_sections(\n    url='https://docs.aws.amazon.com/lambda/latest/dg/python-handler.html',\n    section_titles=[\n        'Example Python Lambda function code',\n        'Code best practices for Python Lambda functions',\n    ],\n)\n```\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to read\n    section_titles: List of section titles to extract\n\nReturns:\n    Filtered markdown content containing only the requested sections\n","after":"Extract specific sections from AWS documentation pages by title.\n\nRetrieves a page, converts to markdown, and returns only matching sections.\nSection matching is case-insensitive and handles whitespace differences.\n\nA title can be a heading at any level. Each section runs to the next heading at the same or\na higher level, so it includes its subsections. A title that names only the page returns\nthe whole page, paginated like read_documentation; if the page title is also a section\nheading, those sections are returned instead.\n\n## URL Requirements\n- Must end with .html or .md\n\n## Large Tables\n\nTables with more than 20 rows are automatically truncated to show only the header and 5 sample rows,\nalong with a hint to use the `search_table` tool. Use `search_table` to filter and retrieve specific\nrows from large tables (e.g., service quotas, IAM actions).\n\n## Read Sections Tips\n\n- Use exact section titles from search results 'sections' field when available\n- Section matching is case-insensitive and handles whitespace differences\n- Include multiple related sections in one call for comprehensive coverage\n- Links to other pages are kept as published, often relative (e.g. `invocation-sync.md`);\n  resolve a relative link against the page URL before reading it\n\n## Example Usage\n\n```\n# If query is about S3 bucket naming rules:\n# Available sections: ['General purpose buckets naming rules', 'Example general purpose bucket names', 'Best practices', 'Creating a bucket that uses a GUID in the bucket name']\n# Read these specific sections:\nread_sections(\n    url='https://docs.aws.amazon.com/s3/latest/userguide/bucketnamingrules.html',\n    section_titles=['General purpose buckets naming rules', 'Best practices'],\n)\n\n# If query is about Python Lambda function examples:\n# Available sections: ['Example Python Lambda function code', 'Handler naming conventions', 'Using the Lambda event object', 'Accessing and using the Lambda context object'. 'Valid handler signatures for Python handlers', 'Returning a value', 'Using the AWS SDK for Python (Boto3) in your handler', 'Accessing environment variables, 'Code best practices for Python Lambda functions']\n# Read these specific sections:\nread_sections(\n    url='https://docs.aws.amazon.com/lambda/latest/dg/python-handler.html',\n    section_titles=[\n        'Example Python Lambda function code',\n        'Code best practices for Python Lambda functions',\n    ],\n)\n```\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to read\n    section_titles: List of section titles to extract\n\nReturns:\n    Filtered markdown content containing only the requested sections\n"},{"tool":"recommend","description":true,"schema":false,"before":"Get content recommendations for an AWS documentation page.\n\n## Usage\n\nThis tool provides recommendations for related AWS documentation pages based on a given URL.\nUse it to discover additional relevant content that might not appear in search results.\n\n## Recommendation Types\n\nThe recommendations include three categories:\n\n1. **New**: Recently added pages within the same AWS service - useful for finding newly released features\n2. **Similar**: Pages covering similar topics to the current page\n3. **Journey**: Pages commonly viewed next by other users\n\n## When to Use\n\n- After reading a documentation page to find related content\n- When exploring a new AWS service to discover important pages\n- To find alternative explanations of complex concepts\n- To find newly released information by using a service's welcome page URL and checking the **New** recommendations\n\n## Finding New Features\n\nTo find newly released information about a service:\n1. Find any page belong to that service, typically you can try the welcome page\n2. Call this tool with that URL\n3. Look specifically at the **New** recommendation type in the results\n\n## Result Interpretation\n\nEach recommendation includes:\n- url: The documentation page URL\n- title: The page title\n- context: A brief description (if available)\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to get recommendations for\n\nReturns:\n    List of recommended pages with URLs, titles, and context\n","after":"Get content recommendations for an AWS documentation page.\n\n## Usage\n\nThis tool provides recommendations for related AWS documentation pages based on a given URL.\nUse it to discover additional relevant content that might not appear in search results.\n\n## Recommendation Types\n\nThe recommendations include three categories:\n\n1. **New**: Recently added pages within the same AWS service - useful for finding newly released features\n2. **Similar**: Pages covering similar topics to the current page\n3. **Journey**: Pages commonly viewed next by other users\n\n## When to Use\n\n- After reading a documentation page to find related content\n- When exploring a new AWS service to discover important pages\n- To find alternative explanations of complex concepts\n- To find newly released information by using a service's welcome page URL and checking the **New** recommendations\n\n## Finding New Features\n\nTo find newly released information about a service:\n1. Find any page belong to that service, typically you can try the welcome page\n2. Call this tool with that URL\n3. Look specifically at the **New** recommendation type in the results\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- A .md page URL, such as a link followed from read_documentation output, is looked up as its .html page\n\n## Result Interpretation\n\nEach recommendation includes:\n- url: The documentation page URL\n- title: The page title\n- context: A brief description (if available)\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: URL of the AWS documentation page to get recommendations for\n\nReturns:\n    List of recommended pages with URLs, titles, and context\n"},{"tool":"search_table","description":true,"schema":false,"before":"Search for specific rows in a large documentation table.\n\nUse this tool when you need specific rows from a large documentation table\n(e.g., service quotas, pricing tables, supported models lists). Returns\nmatching rows as JSON instead of dumping the entire table.\n\nThis is more efficient than read_sections for pages with hundreds of table rows.\nIf read_sections or read_documentation indicates a table was truncated, use this\ntool to find the specific rows you need.\n\n## Section Title\n\n- If you know the exact section title, provide it for precision\n- If unsure, omit section_title — the tool will search all tables on the page\n- Use section titles from search_documentation results (TOC) or read_documentation output\n- If the section title is wrong, the hint field will list available sections\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html\n\n## Example Usage\n\n```\n# With section title (searches all tables in that section):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    section_title='Amazon Bedrock service quotas',\n    query='Titan Text Embeddings V2',\n)\n\n# Without section title (searches all tables on the page):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    query='Claude 3 Sonnet requests',\n)\n```\n\n## Response Format\n\nReturns a SearchTableResponse with:\n- tables_searched: Number of tables searched\n- tables_with_matches: Number of tables containing matching rows\n- hint: Guidance message when no matches found, section not found, or no tables on page\n- results: Array of table result objects, each with:\n    - table_heading: The sub-heading above the table (if any)\n    - columns: Column headers for that table\n    - parent_columns: (optional) For rowspan/nested tables, which columns are group headers\n    - child_columns: (optional) For rowspan/nested tables, which columns are nested under groups\n    - total_rows: Total rows (or groups, for nested tables) in that table\n    - matched_rows: Number of rows/groups matching the query per table\n    - showing: Number of rows/groups returned per table (capped by max_rows per table)\n    - rows: Array of matching row objects. For flat tables: {column → value}.\n      For nested tables: {parent_col → value, ..., \"rows\": [{child_col → value}, ...]}\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: AWS documentation page URL (must end with .html)\n    section_title: The section heading containing the table (optional — omit to search all tables on the page)\n    query: Search term to filter rows (all words must match, case-insensitive)\n    max_rows: Maximum matching rows to return per table (default 20)\n\nReturns:\n    SearchTableResponse with matching rows grouped by table\n","after":"Search for specific rows in a large documentation table.\n\nUse this tool when you need specific rows from a large documentation table\n(e.g., service quotas, pricing tables, supported models lists). Returns\nmatching rows as JSON instead of dumping the entire table.\n\nThis is more efficient than read_sections for pages with hundreds of table rows.\nIf read_sections or read_documentation indicates a table was truncated, use this\ntool to find the specific rows you need.\n\n## Section Title\n\n- If you know the exact section title, provide it for precision\n- If unsure, omit section_title — the tool will search all tables on the page\n- Use section titles from search_documentation results (TOC) or read_documentation output\n- If the section title is wrong, the hint field will list available sections\n\n## URL Requirements\n\n- Must be from the docs.aws.amazon.com domain\n- Must end with .html or .md\n\n## Example Usage\n\n```\n# With section title (searches all tables in that section):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    section_title='Amazon Bedrock service quotas',\n    query='Titan Text Embeddings V2',\n)\n\n# Without section title (searches all tables on the page):\nsearch_table(\n    url='https://docs.aws.amazon.com/general/latest/gr/bedrock.html',\n    query='Claude 3 Sonnet requests',\n)\n```\n\n## Response Format\n\nReturns a SearchTableResponse with:\n- tables_searched: Number of tables searched\n- tables_with_matches: Number of tables containing matching rows\n- hint: Guidance message when no matches found, section not found, or no tables on page\n- results: Array of table result objects, each with:\n    - table_heading: The sub-heading above the table (if any)\n    - columns: Column headers for that table\n    - parent_columns: (optional) For rowspan/nested tables, which columns are group headers\n    - child_columns: (optional) For rowspan/nested tables, which columns are nested under groups\n    - total_rows: Total rows (or groups, for nested tables) in that table\n    - matched_rows: Number of rows/groups matching the query per table\n    - showing: Number of rows/groups returned per table (capped by max_rows per table)\n    - rows: Array of matching row objects. For flat tables: {column → value}.\n      For nested tables: {parent_col → value, ..., \"rows\": [{child_col → value}, ...]}\n\nArgs:\n    ctx: MCP context for logging and error handling\n    url: AWS documentation page URL (must end with .html or .md)\n    section_title: The section heading containing the table (optional — omit to search all tables on the page)\n    query: Search term to filter rows (all words must match, case-insensitive)\n    max_rows: Maximum matching rows to return per table (default 20)\n\nReturns:\n    SearchTableResponse with matching rows grouped by table\n"}]}]}}