AWS location documentation change
Summary
Restructured documentation to focus on specific AI agent implementations (Kiro, Claude Code, Cursor), added installation instructions, and replaced generic MCP server configuration details with agent-specific guidance
Security assessment
The changes primarily reorganize content for different user groups and AI tools without addressing security vulnerabilities. While previous MCP server configurations mentioned credential requirements, these were removed rather than being security-enhanced. The new AWS MCP Server reference links to general documentation without security-specific content
Diff
diff --git a/location/latest/developerguide/ai-llms.md b/location/latest/developerguide/ai-llms.md index 1df90049d..62f88f82c 100644 --- a//location/latest/developerguide/ai-llms.md +++ b//location/latest/developerguide/ai-llms.md @@ -5 +5 @@ -Recommended MCP ServersUseful ContextKiro Agent Configuration +For Kiro usersFor Claude Code and Cursor usersFor other AI coding agentsFor direct context usageMCP Servers @@ -7 +7 @@ Recommended MCP ServersUseful ContextKiro Agent Configuration -# Working with AI and LLMs +# Build with AI agents @@ -9 +9 @@ Recommended MCP ServersUseful ContextKiro Agent Configuration -AI and LLMs can significantly accelerate development with Amazon Location Service by providing intelligent assistance for API usage, code generation, and troubleshooting. By configuring your LLM client with the right MCP servers and context, you can create a powerful development assistant that understands AWS services and Amazon Location Service specifics. Using a minimal context and MCP configuration as recommended on this page can ensure your LLM model of choice has enough context to lead to correct results without overwhelming the context window. This can reduce hallucinations and increase result accuracy. This configuration also ensures that model knowledge cutoff does not impact the quality of the results. +AI and LLMs can significantly accelerate development with Amazon Location Service by providing intelligent assistance for API usage, code generation, and troubleshooting. By configuring your LLM client with the right MCP servers and context, you can create a powerful development assistant that understands AWS services and Amazon Location Service specifics. Using a minimal context and MCP configuration as recommended on this page can ensure your LLM model of choice has enough context to lead to correct results without overwhelming the context window. This can reduce hallucinations and increase result accuracy. This configuration also ensures that model knowledge cutoff does not impact the quality of the results. The Amazon Location Service agent context package provides ready-to-use integrations for popular AI coding assistants, guiding AI agents through adding maps, places search, geocoding, routing, and other geospatial features, including authentication setup, SDK integration, and best practices. Choose the installation method that matches your development environment. @@ -11 +11 @@ AI and LLMs can significantly accelerate development with Amazon Location Servic -## Recommended MCP Servers +## For Kiro users @@ -13 +13 @@ AI and LLMs can significantly accelerate development with Amazon Location Servic -Model Context Protocol (MCP) servers extend LLM capabilities by providing access to external tools, documentation, and APIs. While these MCP servers are not required, they can help the LLM look up additional information about the service and let you stay up to date on the latest Amazon Location Service developer guidance. For Amazon Location Service development, the following MCP servers are recommended: +[Kiro](https://kiro.dev) supports Amazon Location Service through both the Kiro IDE (as a power) and the Kiro CLI (as an Agent Skill). @@ -15 +15 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access - * **[aws-knowledge-mcp-server](https://awslabs.github.io/mcp/servers/aws-knowledge-mcp-server)** \- Access to AWS documentation, API references, best practices, and knowledge bases. Does not require AWS credentials or authentication, making it ideal for documentation lookup without credential management. +Kiro IDE @@ -17 +16,0 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access - * **[aws-api-mcp-server](https://awslabs.github.io/mcp/servers/aws-api-mcp-server)** \- Direct AWS API interactions and CLI command execution. Requires AWS credentials. @@ -18,0 +18 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access +Install Amazon Location Service as a power using the one-click install link: @@ -19,0 +20 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access +[Install Amazon Location Service power in Kiro](https://kiro.dev/launch/powers/amazon-location-service) @@ -20,0 +22 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access +###### Tip @@ -22 +24 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access -### Client Configuration +Alternatively, open Kiro IDE, navigate to the **Powers** panel, select the **Available** tab, and search for "Build geospatial applications with Amazon Location Service". @@ -24 +26 @@ Model Context Protocol (MCP) servers extend LLM capabilities by providing access -Configure your LLM client with the MCP servers using the appropriate configuration format for your client. +###### Note @@ -26 +28 @@ Configure your LLM client with the MCP servers using the appropriate configurati -Kiro +When using [Spec](https://kiro.dev/docs/specs/) mode, include "use the Amazon Location Service power" in your spec prompt for Kiro to activate it. @@ -27,0 +30 @@ Kiro +Kiro CLI @@ -29 +31,0 @@ Kiro -**One-click install:** @@ -31 +33 @@ Kiro - * [AWS Knowledge MCP Server](https://kiro.dev/launch/mcp/add?name=aws-knowledge-mcp&config=%7B%22url%22%3A%22https%3A%2F%2Fknowledge-mcp.global.api.aws%22%2C%22type%22%3A%22http%22%7D) +Install Amazon Location Service as an [Agent Skill](https://agentskills.io) using the skills CLI: @@ -33 +34,0 @@ Kiro - * [AWS API MCP Server](https://kiro.dev/launch/mcp/add?name=awslabs.aws-api-mcp-server&config=%7B%22command%22%3A%20%22uvx%22%2C%20%22args%22%3A%20%5B%22awslabs.aws-api-mcp-server%40latest%22%5D%2C%20%22disabled%22%3A%20false%2C%20%22autoApprove%22%3A%20%5B%5D%7D) @@ -34,0 +36 @@ Kiro + npx skills add aws-geospatial/amazon-location-agent-context -a kiro-cli @@ -36,5 +38 @@ Kiro - - -**Manual configuration:** - -Add the following to your Kiro agent configuration. For more information about [Kiro configuration](https://kiro.dev/docs/mcp/configuration/), see the Kiro documentation. +After installing, add the skill to your custom agent's resources in `.kiro/agents/<agent>.json`: @@ -44,14 +42,3 @@ Add the following to your Kiro agent configuration. For more information about [ - "mcpServers": { - "aws-knowledge-mcp-server": { - "url": "https://knowledge-mcp.global.api.aws", - "type": "http" - }, - "aws-api-mcp-server": { - "command": "uvx", - "args": ["awslabs.aws-api-mcp-server@latest"], - "env": { - "AWS_REGION": "us-east-1", - "READ_OPERATIONS_ONLY": "true" - } - } - } + "resources": [ + "skill://.kiro/skills/**/SKILL.md" + ] @@ -60 +47 @@ Add the following to your Kiro agent configuration. For more information about [ -VSCode with Copilot +###### Note @@ -61,0 +49 @@ VSCode with Copilot +Kiro CLI skill installations don't include MCP configuration automatically. See MCP Servers for manual setup. @@ -63 +51 @@ VSCode with Copilot -**One-click install:** +Once installed, Amazon Location Service activates automatically when you mention keywords like "location", "maps", "geocoding", "routing", "places", "geofencing", or "tracking" in your prompts. @@ -65 +53 @@ VSCode with Copilot - * [AWS Knowledge MCP Server](https://vscode.dev/redirect/mcp/install?name=aws-knowledge-mcp&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fknowledge-mcp.global.api.aws%22%7D) +## For Claude Code and Cursor users @@ -67 +55 @@ VSCode with Copilot - * [AWS API MCP Server](https://insiders.vscode.dev/redirect/mcp/install?name=AWS%20API%20MCP%20Server&config=%7B%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22awslabs.aws-api-mcp-server%40latest%22%5D%2C%22env%22%3A%7B%22AWS_REGION%22%3A%22us-east-1%22%7D%2C%22type%22%3A%22stdio%22%7D) +For Claude Code and Cursor users, install the **amazon-location-service** plugin from the [Agent Plugins for AWS](https://github.com/awslabs/agent-plugins) marketplace. The plugin includes MCP configuration automatically. @@ -68,0 +57 @@ VSCode with Copilot +Claude Code @@ -70,0 +60 @@ VSCode with Copilot +Run the following commands to add the marketplace and install the plugin: @@ -72 +62 @@ VSCode with Copilot -**Manual configuration:** +Add the marketplace: @@ -74 +63,0 @@ VSCode with Copilot -Add the following to your VSCode mcp.json file. For more information about [MCP servers in VS Code](https://code.visualstudio.com/docs/copilot/customization/mcp-servers), see the VSCode documentation. @@ -75,0 +65 @@ Add the following to your VSCode mcp.json file. For more information about [MCP + /plugin marketplace add awslabs/agent-plugins @@ -77,19 +67 @@ Add the following to your VSCode mcp.json file. For more information about [MCP - { - "servers": { - "aws-knowledge-mcp-server": { - "type": "http", - "url": "https://knowledge-mcp.global.api.aws" - }, - "aws-api-mcp-server": { - "command": "uvx", - "args": ["awslabs.aws-api-mcp-server@latest"], - "env": { - "AWS_REGION": "us-east-1", - "READ_OPERATIONS_ONLY": "true" - } - } - } - } - -VSCode with Cline - +Install the plugin: @@ -97 +68,0 @@ VSCode with Cline -**Manual configuration:** @@ -99,20 +70 @@ VSCode with Cline -Add the following to your Cline MCP settings file (cline_mcp_settings.json). For more information about [Cline MCP configuration](https://docs.cline.bot/mcp/configuring-mcp-servers), see the Cline documentation. - - - { - "mcpServers": { - "aws-knowledge-mcp-server": { - "type": "streamableHttp", - "url": "https://knowledge-mcp.global.api.aws" - }, - "aws-api-mcp-server": { - "type": "stdio", - "command": "uvx", - "args": ["awslabs.aws-api-mcp-server@latest"], - "env": { - "AWS_REGION": "us-east-1", - "READ_OPERATIONS_ONLY": "true" - } - } - } - } + /plugin install amazon-location-service@agent-plugins-for-aws @@ -123 +75 @@ Cursor -**Manual configuration:** +You can install the **amazon-location-service** plugin from the [Cursor Marketplace](https://cursor.com/marketplace/aws). For additional information, see the [Cursor plugin documentation](https://docs.cursor.com/plugins). You can also install within the Cursor application: @@ -125 +77 @@ Cursor -Add the following to your Cursor mcp.json file. For more information about [Cursor MCP configuration](https://cursor.com/docs/context/mcp), see the Cursor documentation. + 1. Open Cursor Settings. @@ -126,0 +79 @@ Add the following to your Cursor mcp.json file. For more information about [Curs + 2. Navigate to **Plugins**. @@ -128,18 +81 @@ Add the following to your Cursor mcp.json file. For more information about [Curs - { - "mcpServers": { - "aws-knowledge-mcp-server": { - "url": "https://knowledge-mcp.global.api.aws" - }, - "aws-api-mcp-server": { - "command": "uvx", - "args": ["awslabs.aws-api-mcp-server@latest"], - "env": { - "AWS_REGION": "us-east-1", - "READ_OPERATIONS_ONLY": "true" - } - } - } - } - -Claude Code - + 3. Search for **AWS**. @@ -147 +83 @@ Claude Code -**Manual configuration:** + 4. Select the **amazon-location-service** plugin and choose **Add to Cursor**. @@ -149 +85 @@ Claude Code -Add MCP servers using the Claude CLI commands. For more information about [Claude Code MCP setup](https://code.claude.com/docs/en/mcp), see the Claude Code documentation. + 5. Select the scope for the installed plugin. @@ -152,2 +87,0 @@ Add MCP servers using the Claude CLI commands. For more information about [Claud - # Add AWS Knowledge MCP Server (HTTP) - claude mcp add --transport http aws-knowledge-mcp-server https://knowledge-mcp.global.api.aws @@ -155,2 +88,0 @@ Add MCP servers using the Claude CLI commands. For more information about [Claud - # Add AWS API MCP Server (stdio) - claude mcp add --transport stdio aws-api-mcp-server -- uvx awslabs.aws-api-mcp-server@latest @@ -158 +90 @@ Add MCP servers using the Claude CLI commands. For more information about [Claud -Gemini Code Assist +The plugin should appear under **Plugins** > **Installed**. @@ -159,0 +92 @@ Gemini Code Assist +## For other AI coding agents @@ -161 +94 @@ Gemini Code Assist -**Manual configuration:** +For AI coding agents that support the [Agent Skills](https://agentskills.io) open standard (including GitHub Copilot, OpenCode, Codex, Antigravity, and [more](https://github.com/vercel-labs/skills?tab=readme-ov-file#supported-agents)), install the skill using the skills CLI: @@ -163 +95,0 @@ Gemini Code Assist -Add the following to your Gemini settings JSON file (~/.gemini/settings.json). For more information about [Gemini Code Assist MCP configuration](https://developers.google.com/gemini-code-assist/docs/use-agentic-chat-pair-programmer#configure-mcp-servers), see the Google Cloud documentation. @@ -164,0 +97 @@ Add the following to your Gemini settings JSON file (~/.gemini/settings.json). F + npx skills add aws-geospatial/amazon-location-agent-context @@ -166,17 +99 @@ Add the following to your Gemini settings JSON file (~/.gemini/settings.json). F - { - "mcpServers": {