# AWS Knowledge MCP server > Search and read AWS documentation, API references, What's New posts and regional availability for services, APIs and CloudFormation… - Listing: https://mcp.tc/i/aws-knowledge - Connect: use the server's own URL `https://knowledge-mcp.global.api.aws` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: none - Category: [Docs & Knowledge](https://mcp.tc/c/docs-knowledge) - Vendor: Amazon Web Services - Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe. - Homepage: - Repository: ## About A managed remote server from AWS that gives an assistant access to official AWS content: documentation, API references, troubleshooting guides, What's New posts, blog posts, Well-Architected guidance, Amplify, CDK and CloudFormation docs, and Strands Agents SDK docs. It can also report regional availability for services, SDK APIs and CloudFormation resources, and retrieve AWS agent skills. It runs as a hosted endpoint using Streamable HTTP at https://knowledge-mcp.global.api.aws and needs no authentication. Clients without remote MCP support can use a stdio proxy such as fastmcp. ## What it can do - Search AWS docs with topic filters such as reference or troubleshooting - Read full AWS documentation pages as markdown - List all AWS regions - Check regional availability of services, APIs and CloudFormation resources - Retrieve AWS agent skills with workflows and references - Find CDK, CloudFormation and Amplify guidance ## Tools (5) - `aws___read_documentation`: Fetch full AWS documentation pages as markdown when search chunks lack the needed detail. (read-only) - `aws___search_documentation`: Search AWS docs by topic and return verbatim page chunks. (read-only) - `aws___list_regions`: List all AWS regions. (read-only) - `aws___get_regional_availability`: Check availability of products, service APIs or CloudFormation resources per region. (read-only) - `aws___retrieve_skill`: Retrieve an AWS skill's SKILL.md or a specific file, using a name from search results. (read-only) ## Example prompts - "Which AWS regions support Amazon Bedrock?" - "What did AWS announce recently for Lambda?" - "How do I fix an AccessDenied error when calling S3 PutObject?" - "Show CDK best practices for defining an SQS queue with a dead-letter queue." ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http aws-knowledge https://knowledge-mcp.global.api.aws ``` 2. Start Claude Code and type `/mcp`. **aws-knowledge** should show as connected. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **AWS Knowledge** and paste this URL: ```url https://knowledge-mcp.global.api.aws ``` 3. Click **Add**. Its tools appear in the chat’s tools menu. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://knowledge-mcp.global.api.aws` and click **Add**. 3. Turn it on in a chat from the tools menu. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://knowledge-mcp.global.api.aws` as the server URL and choose **No authentication**. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "aws-knowledge": { "url": "https://knowledge-mcp.global.api.aws" } } } ``` ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"aws-knowledge","type":"http","url":"https://knowledge-mcp.global.api.aws"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "aws-knowledge": { "type": "http", "url": "https://knowledge-mcp.global.api.aws" } } } ``` ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "aws-knowledge": { "serverUrl": "https://knowledge-mcp.global.api.aws" } } } ``` 2. Refresh the MCP server list in Cascade. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add aws-knowledge --url https://knowledge-mcp.global.api.aws ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.aws-knowledge] url = "https://knowledge-mcp.global.api.aws" ``` ### Gemini CLI ```bash gemini mcp add --transport http aws-knowledge https://knowledge-mcp.global.api.aws ``` This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "aws-knowledge": { "type": "http", "url": "https://knowledge-mcp.global.api.aws" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://knowledge-mcp.global.api.aws`. ## Details - Server version: 1.0.0 - MCP protocol version: 2025-03-26 - Last checked: 2026-10-03 (reachable) - Listed: 2026-10-03 - Updated: 2026-10-04 --- Source: https://mcp.tc/i/aws-knowledge (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report