AWS solutions medium security documentation change
Summary
Updated MCP integration documentation with rebranded tool names (Amazon Q CLI to Kiro CLI, Amazon Q Suite to Amazon Quick), corrected MCP endpoint URL format, added Bearer token authentication, and revised Cognito credential retrieval steps.
Security assessment
The change introduces Bearer token authentication (Authorization: 'Bearer <access-token>') replacing plaintext tokens, which enforces secure authentication standards. It also adds explicit warnings about token security: 'Keep your access token secure and do not share it publicly. The token provides read/write access to your load testing data.' These updates directly address authentication security weaknesses.
Diff
diff --git a/solutions/latest/distributed-load-testing-on-aws/mcp-server-integration.md b/solutions/latest/distributed-load-testing-on-aws/mcp-server-integration.md index b8629c956..bda999877 100644 --- a//solutions/latest/distributed-load-testing-on-aws/mcp-server-integration.md +++ b//solutions/latest/distributed-load-testing-on-aws/mcp-server-integration.md @@ -9 +9 @@ Step 1: Get MCP endpoint and access tokenStep 2: Test with MCP InspectorStep 3: -# MCP server integration +# MCP Server integration @@ -11 +11 @@ Step 1: Get MCP endpoint and access tokenStep 2: Test with MCP InspectorStep 3: -If you deployed the optional MCP server component during solution deployment, you can integrate the Distributed Load Testing solution with AI development tools that support the Model Context Protocol. The MCP server provides programmatic access to retrieve, manage, and analyze load tests through AI assistants. +If you deployed the optional MCP Server component during solution deployment, you can integrate the Distributed Load Testing solution with AI development tools that support the Model Context Protocol. The MCP Server provides programmatic access to retrieve, manage, and analyze load tests through AI assistants. @@ -13 +13 @@ If you deployed the optional MCP server component during solution deployment, yo -Customers can connect to the DLT MCP Server using the client of their choice (Amazon Q, Claude, etc.), which each have slightly different configuration instructions. This section provides setup instructions for MCP Inspector, Amazon Q CLI, Cline, and Amazon Q Suite. +Customers can connect to the DLT MCP Server using the client of their choice (Amazon Q, Claude, etc.), which each have slightly different configuration instructions. This section provides setup instructions for MCP Inspector, Kiro CLI, Cline, and Amazon Quick. @@ -17 +17 @@ Customers can connect to the DLT MCP Server using the client of their choice (Am -Before configuring any MCP client, you need to retrieve your MCP server endpoint and access token from the DLT web console. +Before configuring any MCP client, you need to retrieve your MCP Server endpoint and access token from the DLT web console. @@ -40 +40 @@ Keep your access token secure and do not share it publicly. The token provides r -The Model Context Protocol offers [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector), a tool to directly connect to MCP servers and invoke tools. This provides a convenient UI and sample network requests for testing your MCP server connection before configuring AI clients. +The Model Context Protocol offers [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector), a tool to directly connect to MCP servers and invoke tools. This provides a convenient UI and sample network requests for testing your MCP Server connection before configuring AI clients. @@ -89 +89 @@ Once connected, you can test the available MCP tools: -After verifying your MCP server connection with MCP Inspector, you can configure your preferred AI development client. +After verifying your MCP Server connection with MCP Inspector, you can configure your preferred AI development client. @@ -91 +91 @@ After verifying your MCP server connection with MCP Inspector, you can configure -### Amazon Q CLI +### Kiro CLI @@ -93 +93 @@ After verifying your MCP server connection with MCP Inspector, you can configure -Amazon Q CLI provides command-line access to AI-assisted development with MCP server integration. +Kiro CLI (formerly Amazon Q Developer CLI) provides command-line access to AI-assisted development with MCP Server integration. @@ -97 +97 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se - 1. Edit the `mcp.json` configuration file. For more information on configuration file location, refer to [Configuring remote MCP servers](https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/command-line-mcp-config-CLI.html#command-line-mcp-remote-servers) in the _Amazon Q Developer User Guide_. + 1. Edit the `mcp.json` configuration file. For more information on configuration file location, refer to [Model Context Protocol (MCP)](https://kiro.dev/docs/cli/mcp/) in the _Kiro CLI documentation_. @@ -99 +99 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se - 2. Add your DLT MCP server configuration: + 2. Add your DLT MCP Server configuration: @@ -105 +105 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se - "url": "https://[api-id].execute-api.[region].amazonaws.com/[stage]/gateway/backend-agent/sse/mcp", + "url": "https://<gateway-id>.gateway.bedrock-agentcore.<region>.amazonaws.com/mcp", @@ -107 +107 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se - "Authorization": "your_access_token_here" + "Authorization": "Bearer <access-token>" @@ -115,0 +116,2 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se +Replace `<gateway-id>` and `<region>` with the values from your MCP Server Endpoint URL, and `<access-token>` with the value you copied in Step 1. + @@ -118 +120 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se - 1. In a terminal, type `q` to launch Amazon Q CLI. + 1. In a terminal, type `kiro-cli` to launch Kiro CLI. @@ -131 +133 @@ Amazon Q CLI provides command-line access to AI-assisted development with MCP se -Cline is an AI coding assistant that supports MCP server integration. +Cline is an AI coding assistant that supports MCP Server integration. @@ -143 +145 @@ Cline is an AI coding assistant that supports MCP server integration. - "url": "https://[api-id].execute-api.[region].amazonaws.com/[stage]/gateway/backend-agent/sse/mcp", + "url": "https://<gateway-id>.gateway.bedrock-agentcore.<region>.amazonaws.com/mcp", @@ -145 +147 @@ Cline is an AI coding assistant that supports MCP server integration. - "Authorization": "your_access_token_here" + "Authorization": "Bearer <access-token>" @@ -150,0 +153,2 @@ Cline is an AI coding assistant that supports MCP server integration. +Replace `<gateway-id>` and `<region>` with the values from your MCP Server Endpoint URL, and `<access-token>` with the value you copied in Step 1. + @@ -158 +162 @@ Cline is an AI coding assistant that supports MCP server integration. -### Amazon Q Suite +### Amazon Quick @@ -160 +164 @@ Cline is an AI coding assistant that supports MCP server integration. -Amazon Q Suite provides a comprehensive AI assistant platform with support for MCP server actions. +Amazon Quick (formerly Amazon Quick Suite) provides a comprehensive AI assistant platform with support for MCP Server actions. @@ -164 +168 @@ Amazon Q Suite provides a comprehensive AI assistant platform with support for M -Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth credentials from your DLT deployment’s Cognito user pool: +Before configuring the MCP Server in Amazon Quick, you need to retrieve OAuth credentials from your DLT deployment’s Cognito user pool: @@ -172,2 +175,0 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - - @@ -180,5 +182 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - - - 7. Locate the app client with the name ending in `m2m` (machine-to-machine). - - 8. Copy the **Client ID** and **Client secret**. + 7. Locate the app client with the name ending in `m2m` (machine-to-machine) and select it. @@ -186 +184 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - 9. Get the user pool domain from the **Domain** tab. + 8. On the app client details page, copy the **Client ID**. To reveal the **Client secret** , choose **Show client secret** , then copy the value. @@ -188 +186 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - + 9. Return to the user pool and get the user pool domain from the **Domain** tab. @@ -197 +195 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - 1. In Amazon Q Suite, create a new agent or select an existing agent. + 1. In Amazon Quick, create a new agent or select an existing agent. @@ -199 +197 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - 2. Add an agent prompt that describes how to interact with the DLT MCP server. + 2. Add an agent prompt that describes how to interact with the DLT MCP Server. @@ -201 +199 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - 3. Add a new action and select **MCP server action**. + 3. Add a new action and select **MCP Server action**. @@ -203,5 +201 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - - - - - 4. Configure the MCP server details: + 4. Configure the MCP Server details: @@ -211,2 +204,0 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - - @@ -221,3 +213 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - - - 5. Save the MCP server action configuration. + 5. Save the MCP Server action configuration. @@ -225 +215 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - 6. Add the new MCP server action to your agent. + 6. Add the new MCP Server action to your agent. @@ -232 +222 @@ Before configuring the MCP server in Amazon Q Suite, you need to retrieve OAuth - 1. Launch the agent in Amazon Q Suite. + 1. Launch the agent in Amazon Quick. @@ -249 +239 @@ For detailed information about available MCP tools and their parameters, refer t -Natual language interaction with the MCP Server can be as simple as `Show me the load tests that have completed in the last 24 hours with their associated completion status` or can be more descriptive such as +Natural language interaction with the MCP Server can be as simple as `Show me the load tests that have completed in the last 24 hours with their associated completion status` or can be more descriptive such as @@ -319 +309 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Explore test results +CloudWatch Alarms @@ -321 +311 @@ Explore test results -Developer guide +Troubleshooting