@aws/nx-plugin-mcp 1.0.0-rc.20 → 1.0.0-rc.22

package/docs/guides/py-agent.mdx

@@ -4,7 +4,9 @@ description: Generate a Python Agent for building AI agents with tools and deplo
 generator: py#agent
 ---
 
-import { FileTree, Tabs, TabItem } from '@astrojs/starlight/components';
+import { FileTree, Tabs, TabItem, CardGrid } from '@astrojs/starlight/components';
+import Astro from '@astrojs/react';
+import ConnectionCard from '@components/connection-card.astro';
 import RunGenerator from '@components/run-generator.astro';
 import NxCommands from '@components/nx-commands.astro';
 import Link from '@components/link.astro';
@@ -14,18 +16,9 @@ import GeneratorParameters from '@components/generator-parameters.astro';
 import Drawer from '@components/drawer.astro';
 import OptionFilter from '@components/option-filter.astro';
 
-Generate a Python [Strands Agent](https://strandsagents.com/) for building AI agents with tools, and optionally deploy it to [Amazon Bedrock AgentCore Runtime](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/). By default, the generator uses [FastAPI](https://fastapi.tiangolo.com/) to expose an HTTP server. Alternatively, you can choose the [Agent-to-Agent (A2A)](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-a2a.html) protocol for interoperability with other A2A-compatible agents, or the [AG-UI](https://docs.ag-ui.com/) protocol for direct frontend integration via [CopilotKit](https://docs.copilotkit.ai/aws-strands).
+Generate a Python AI agent for building agents with tools, and optionally deploy it to [Amazon Bedrock AgentCore Runtime](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/). Choose the agent framework with the `framework` option: [Strands](https://strandsagents.com/) (the default) or [LangChain](https://docs.langchain.com/oss/python/langchain/overview) (built on [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview)).
 
-## What is Strands?
-
-[Strands](https://strandsagents.com/docs/user-guide/quickstart/overview/) is a lightweight, production-ready Python framework for building AI agents. Key features include:
-
-- **Lightweight and customizable**: Simple agent loop that gets out of your way
-- **Production ready**: Full observability, tracing, and deployment options for scale
-- **Model and provider agnostic**: Supports many different models from various providers
-- **Community-driven tools**: Powerful set of community-contributed tools
-- **Multi-agent support**: Advanced techniques like agent teams and autonomous agents
-- **Flexible interaction modes**: Conversational, streaming, and non-streaming support
+The generator exposes your agent over a server `protocol`. Both frameworks support [HTTP](https://fastapi.tiangolo.com/) (the default), the [Agent-to-Agent (A2A)](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-a2a.html) protocol for interoperability with other A2A-compatible agents, and the [AG-UI](https://docs.ag-ui.com/) protocol for direct frontend integration via [CopilotKit](https://docs.copilotkit.ai/).
 
 ## Usage
 
@@ -64,10 +57,10 @@ The generator will add the following files to your existing Python project. The
 </FileTree>
 </OptionFilter>
 
-<OptionFilter when={{ protocol: 'a2a' }} description="Strands A2A server layout">
+<OptionFilter when={{ protocol: 'a2a' }} description="A2A server layout">
 ### A2A Protocol
 
-The entry point uses the [Strands A2A Server](https://strandsagents.com/docs/user-guide/concepts/multi-agent/agent-to-agent) instead of FastAPI:
+The entry point exposes your agent over the A2A protocol (Strands uses the [Strands A2A Server](https://strandsagents.com/docs/user-guide/concepts/multi-agent/agent-to-agent); LangChain wraps the graph in an [`a2a-sdk`](https://a2a-protocol.org/) executor), mounted onto a FastAPI app:
 
 <FileTree>
   - your-project/
@@ -77,7 +70,7 @@ The entry point uses the [Strands A2A Server](https://strandsagents.com/docs/use
         - agent.py Main agent definition with sample tools
         - main.py A2A server entry point
         - Dockerfile Entry point for hosting your agent (excluded when `infra` is set to `None`)
-    - pyproject.toml Updated with Strands dependencies
+    - pyproject.toml Updated with framework and A2A dependencies
     - project.json Updated with agent serve targets
 </FileTree>
 </OptionFilter>
@@ -85,7 +78,7 @@ The entry point uses the [Strands A2A Server](https://strandsagents.com/docs/use
 <OptionFilter when={{ protocol: 'ag-ui' }} description="AG-UI / CopilotKit server layout">
 ### AG-UI Protocol
 
-The entry point uses the [ag-ui-strands](https://docs.ag-ui.com/) integration, which exposes your agent via the AG-UI protocol for direct frontend integration with [CopilotKit](https://docs.copilotkit.ai/aws-strands):
+The entry point exposes your agent via the [AG-UI](https://docs.ag-ui.com/) protocol for direct frontend integration with [CopilotKit](https://docs.copilotkit.ai/). Strands agents use the [ag-ui-strands](https://docs.ag-ui.com/) integration; LangChain agents use [ag-ui-langgraph](https://docs.ag-ui.com/):
 
 <FileTree>
   - your-project/
@@ -93,14 +86,14 @@ The entry point uses the [ag-ui-strands](https://docs.ag-ui.com/) integration, w
       - agent/ (or custom name if specified)
         - \_\_init\_\_.py Python package initialization
         - agent.py Main agent definition with sample tools
-        - main.py AG-UI server entry point using ag-ui-strands
+        - main.py AG-UI server entry point
         - Dockerfile Entry point for hosting your agent (excluded when `infra` is set to `None`)
-    - pyproject.toml Updated with Strands and AG-UI dependencies
+    - pyproject.toml Updated with framework and AG-UI dependencies
     - project.json Updated with agent serve targets
 </FileTree>
 
 :::tip[Connect to a React website]
-AG-UI agents can be connected to a React frontend using the <Link path="/guides/connection/react-agui">`connection` generator</Link>, which will set up [CopilotKit](https://docs.copilotkit.ai/aws-strands) components for a rich chat experience.
+AG-UI agents can be connected to a React frontend using the <Link path="/guides/connection/react-agui">`connection` generator</Link>, which will set up [CopilotKit](https://docs.copilotkit.ai/) components for a rich chat experience.
 :::
 </OptionFilter>
 
@@ -146,12 +139,14 @@ If you selected `none` for `infra`, no CDK constructs or Terraform modules are g
 
 ## Working with Your Agent
 
-### Adding Tools
+You can edit `agent.py` to add tools, configure the model and customize the system prompt. The API depends on the framework you chose.
 
-Tools are functions that the AI agent can call to perform actions. The Strands framework uses a simple decorator-based approach for defining tools.
+### Adding Tools
 
-You can add new tools in the `agent.py` file:
+Tools are functions that the AI agent can call to perform actions. Both frameworks use a decorator-based approach for defining tools, derive the tool name and description from the function name and docstring, and generate the input schema from your type hints.
 
+<Tabs syncKey="agent-framework">
+<TabItem label="Strands" _filter={{ framework: 'strands' }}>
 ```python
 from strands import Agent, tool
 
@@ -172,14 +167,38 @@ agent = Agent(
     tools=[calculate_sum, get_weather],
 )
 ```
+</TabItem>
+<TabItem label="LangChain" _filter={{ framework: 'langchain' }}>
+```python
+from langchain.agents import create_agent
+from langchain_aws import ChatBedrockConverse
+from langchain_core.tools import tool
+
+@tool
+def calculate_sum(numbers: list[int]) -> int:
+    """Calculate the sum of a list of numbers"""
+    return sum(numbers)
 
-The Strands framework automatically handles:
-- Type validation based on your function's type hints
-- JSON schema generation for tool calling
-- Error handling and response formatting
+@tool
+def get_weather(city: str) -> str:
+    """Get weather information for a city"""
+    # Your weather API integration here
+    return f"Weather in {city}: Sunny, 25°C"
+
+# Add tools to your agent
+agent = create_agent(
+    model=ChatBedrockConverse(model=MODEL_ID, region_name=REGION),
+    tools=[calculate_sum, get_weather],
+    system_prompt="You are a helpful assistant with access to various tools.",
+)
+```
+</TabItem>
+</Tabs>
 
 ### Using Pre-built Tools
 
+<Tabs syncKey="agent-framework">
+<TabItem label="Strands" _filter={{ framework: 'strands' }}>
 Strands provides a collection of pre-built tools through the `strands-tools` package:
 
 ```python
@@ -190,9 +209,26 @@ agent = Agent(
     tools=[current_time, http_request, file_read],
 )
 ```
+</TabItem>
+<TabItem label="LangChain" _filter={{ framework: 'langchain' }}>
+LangChain provides a large ecosystem of [tools and integrations](https://docs.langchain.com/oss/python/integrations/tools). Install the relevant integration package, then pass the tools to `create_agent`:
+
+```python
+from langchain_community.tools import DuckDuckGoSearchRun
+
+agent = create_agent(
+    model=ChatBedrockConverse(model=MODEL_ID, region_name=REGION),
+    tools=[DuckDuckGoSearchRun()],
+    system_prompt="You are a helpful assistant.",
+)
+```
+</TabItem>
+</Tabs>
 
 ### Model Configuration
 
+<Tabs syncKey="agent-framework">
+<TabItem label="Strands" _filter={{ framework: 'strands' }}>
 By default, Strands agents use Claude 4 Sonnet, but you can customize the model provider. See the [Strands documentation on model providers](https://strandsagents.com/docs/user-guide/concepts/model-providers/) for configuration options:
 
 ```python
@@ -208,30 +244,45 @@ bedrock_model = BedrockModel(
 
 agent = Agent(model=bedrock_model)
 ```
+</TabItem>
+<TabItem label="LangChain" _filter={{ framework: 'langchain' }}>
+LangChain agents use a [`ChatBedrockConverse`](https://docs.langchain.com/oss/python/integrations/chat/bedrock_converse) model. The generated agent reads the model id and region from the `MODEL_ID` and `AWS_REGION` environment variables, but you can configure the model directly in `agent.py`:
 
-### Consuming MCP Servers
+```python
+from langchain_aws import ChatBedrockConverse
+
+model = ChatBedrockConverse(
+    model="anthropic.claude-sonnet-4-20250514-v1:0",
+    region_name="us-west-2",
+    temperature=0.3,
+)
+```
+</TabItem>
+</Tabs>
 
-You can [add tools from MCP servers](https://strandsagents.com/docs/user-guide/concepts/tools/mcp-tools/) to your Strands agent.
+### Consuming MCP Servers
 
-For consuming MCP Servers which you have created using the <Link path="/guides/py-mcp-server">`py#mcp-server`</Link> or <Link path="/guides/ts-mcp-server">`ts#mcp-server`</Link> generators you can make use of the <Link path="/guides/connection/py-agent-mcp">`connection` generator</Link>.
+For consuming MCP Servers which you have created using the <Link path="/guides/py-mcp-server">`py#mcp-server`</Link> or <Link path="/guides/ts-mcp-server">`ts#mcp-server`</Link> generators you can make use of the <Link path="/guides/connection/py-agent-mcp">`connection` generator</Link>, which wires the MCP server's tools into your agent for both frameworks.
 
 <RunGenerator generator="connection" />
 
 Refer to the <Link path="/guides/connection/py-agent-mcp">`connection` generator guide</Link> for details about how the connection is set up.
 
-For other MCP servers, please refer to the [Strands Documentation](https://strandsagents.com/docs/user-guide/concepts/tools/mcp-tools/).
+For other MCP servers, refer to the [Strands](https://strandsagents.com/docs/user-guide/concepts/tools/mcp-tools/) or [LangChain](https://docs.langchain.com/oss/python/langchain/mcp) MCP documentation.
 
 ### More
 
-For a more in-depth guide to writing Strands agents, refer to the [Strands documentation](https://strandsagents.com/docs/user-guide/quickstart/overview/).
+For a more in-depth guide to writing agents, refer to the [Strands](https://strandsagents.com/docs/user-guide/quickstart/overview/) or [LangChain](https://docs.langchain.com/oss/python/langchain/overview) documentation.
 
 ## Protocol
 
 Your agent's server protocol determines how it communicates. All options are served by [FastAPI](https://fastapi.tiangolo.com/) — the entry point differs:
 
 - **HTTP** (default): A standard FastAPI server with a custom `/invocations` endpoint, CORS, and streaming. Best for custom client integrations.
-- **A2A**: The [Strands A2A Server](https://strandsagents.com/docs/user-guide/concepts/multi-agent/agent-to-agent) mounted onto a FastAPI app. Best when your agent needs to be discoverable and invokable by other A2A-compatible agents.
-- **AG-UI**: The [ag-ui-strands](https://docs.ag-ui.com/) integration, which exposes the [AG-UI protocol](https://docs.ag-ui.com/) over SSE. Best for direct frontend integration with [CopilotKit](https://docs.copilotkit.ai/aws-strands) in a React website.
+- **A2A**: An [Agent-to-Agent](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-a2a.html) server mounted onto a FastAPI app (Strands uses the [Strands A2A Server](https://strandsagents.com/docs/user-guide/concepts/multi-agent/agent-to-agent); LangChain uses the framework-agnostic [`a2a-sdk`](https://a2a-protocol.org/)). Best when your agent needs to be discoverable and invokable by other A2A-compatible agents.
+- **AG-UI**: The [AG-UI protocol](https://docs.ag-ui.com/) over SSE (Strands uses `ag-ui-strands`; LangChain uses `ag-ui-langgraph`). Best for direct frontend integration with [CopilotKit](https://docs.copilotkit.ai/) in a React website.
+
+The server entry point differs by framework (Strands yields a context-managed `Agent`, while LangChain drives a compiled `create_agent` graph), but the external contract for each protocol is the same.
 
 All protocols expose `/ping` for the AgentCore runtime health check contract. A2A agents listen on port `9000`; HTTP and AG-UI agents listen on port `8080`. The generated Dockerfile and infrastructure are configured for you.
 
@@ -322,20 +373,23 @@ Since the generator vends CDK or Terraform infrastructure which manages deployin
 <OptionFilter when={{ protocol: 'a2a' }} description="A2A server details">
 ## A2A Server (A2A protocol)
 
-The generated `main.py` mounts `A2AServer.to_fastapi_app()` onto a parent FastAPI app that also exposes `/ping`. When deployed to AgentCore, the entry point resolves the runtime's public ARN from AppConfig and advertises it in the agent card.
+The generated `main.py` mounts an A2A server onto a parent FastAPI app that also exposes `/ping`. Strands agents use the Strands `A2AServer`; LangChain agents wrap the compiled graph in an [`a2a-sdk`](https://a2a-protocol.org/) `AgentExecutor`. When deployed to AgentCore, the entry point resolves the runtime's public ARN from AppConfig and advertises it in the agent card.
 
-Most users will not need to modify this file — edit `agent.py` to change tools or the system prompt. The A2A server populates the agent card (`/.well-known/agent-card.json`) from the `Agent` constructor's `name` and `description`.
+Most users will not need to modify this file; edit `agent.py` to change tools or the system prompt. The A2A server populates the agent card (`/.well-known/agent-card.json`) from the agent's `name` and `description`.
 </OptionFilter>
 
 <OptionFilter when={{ protocol: 'ag-ui' }} description="AG-UI / CopilotKit server details">
 ## AG-UI Server (AG-UI protocol)
 
-The generated `main.py` wraps your Strands `Agent` in an `ag_ui_strands.StrandsAgent` and creates a FastAPI app via `create_strands_app()`. The resulting app exposes a single POST endpoint that streams [AG-UI](https://docs.ag-ui.com/) events over Server-Sent Events (SSE), as well as `/ping` for the AgentCore runtime health check.
+The generated `main.py` exposes a single POST endpoint that streams [AG-UI](https://docs.ag-ui.com/) events over Server-Sent Events (SSE), as well as `/ping` for the AgentCore runtime health check. The wiring depends on the framework:
+
+- **Strands**: wraps your `Agent` in an `ag_ui_strands.StrandsAgent` and creates the FastAPI app via `create_strands_app()`.
+- **LangChain**: wraps the compiled graph in an `ag_ui_langgraph.LangGraphAgent` and serves it from a hand-rolled FastAPI `/invocations` loop.
 
 Most users will not need to modify this file — edit `agent.py` to change tools or the system prompt.
 
 :::tip[Connecting to a React website]
-AG-UI agents are designed to be consumed directly by a frontend. Use the <Link path="/guides/connection/react-agui">`connection` generator</Link> to wire your React website up to the agent with a [CopilotKit](https://docs.copilotkit.ai/aws-strands) provider and [AG-UI HttpAgent](https://docs.ag-ui.com/) client.
+AG-UI agents are designed to be consumed directly by a frontend. Use the <Link path="/guides/connection/react-agui">`connection` generator</Link> to wire your React website up to the agent with a [CopilotKit](https://docs.copilotkit.ai/) provider and [AG-UI HttpAgent](https://docs.ag-ui.com/) client.
 :::
 </OptionFilter>
 
@@ -514,9 +568,72 @@ Refer to the <Link path="/guides/connection/py-agent-a2a">`connection` generator
 <OptionFilter when={{ protocol: 'ag-ui' }} description="AG-UI / React connection details">
 ### Invoking an AG-UI Agent
 
-To invoke your AG-UI agent from a React website, use the <Link path="/guides/connection/react-agui">`connection` generator</Link>, which wires up a [CopilotKit](https://docs.copilotkit.ai/aws-strands) client configured for your deployed agent with the correct authentication (IAM or Cognito).
+To invoke your AG-UI agent from a React website, use the <Link path="/guides/connection/react-agui">`connection` generator</Link>, which wires up a [CopilotKit](https://docs.copilotkit.ai/) client configured for your deployed agent with the correct authentication (IAM or Cognito).
 
 <RunGenerator generator="connection" />
 
 Refer to the <Link path="/guides/connection/react-agui">`connection` generator guide</Link> for details about how the connection is set up.
 </OptionFilter>
+
+## Connections
+
+Use the <Link path="guides/connection">`connection`</Link> generator to integrate this project with others in your workspace. The following connections involve this project:
+
+<CardGrid>
+  <ConnectionCard
+    title="React to Python Agent"
+    description="Call a Python Agent from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-py-agent`}
+    source="react"
+    target="strands"
+    targetBadge="python"
+  />
+  <ConnectionCard
+    title="React to AG-UI Agent"
+    description="Call an Agent exposing the AG-UI protocol from a React website via CopilotKit"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-agui`}
+    source="react"
+    target="copilotkit"
+  />
+  <ConnectionCard
+    title="Python Agent to MCP"
+    description="Connect a Python Agent to an MCP server"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-agent-mcp`}
+    source="strands"
+    sourceBadge="python"
+    target="mcp"
+  />
+  <ConnectionCard
+    title="Python Agent to A2A Agent"
+    description="Connect a Python Agent to a remote A2A agent"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-agent-a2a`}
+    source="strands"
+    sourceBadge="python"
+    target="a2a"
+  />
+  <ConnectionCard
+    title="TypeScript Agent to A2A Agent"
+    description="Connect a TypeScript Agent to a remote A2A agent"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/ts-agent-a2a`}
+    source="strands"
+    sourceBadge="typescript"
+    target="a2a"
+  />
+  <ConnectionCard
+    title="Python Agent to Python DynamoDB"
+    description="Connect a Python Agent to a DynamoDB table"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-agent-dynamodb`}
+    source="strands"
+    sourceBadge="python"
+    target="dynamodb"
+    targetBadge="python"
+  />
+  <ConnectionCard
+    title="Python Agent to AgentCore Gateway"
+    description="Connect a Python Agent to an AgentCore Gateway"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-agent-gateway`}
+    source="strands"
+    sourceBadge="python"
+    target="agentcore"
+  />
+</CardGrid>

package/docs/guides/py-dynamodb.mdx

@@ -4,7 +4,9 @@ description: Create a Python DynamoDB project
 generator: py#dynamodb
 ---
 
-import { FileTree } from '@astrojs/starlight/components';
+import { FileTree, CardGrid } from '@astrojs/starlight/components';
+import Astro from '@astrojs/react';
+import ConnectionCard from '@components/connection-card.astro';
 import Link from '@components/link.astro';
 import RunGenerator from '@components/run-generator.astro';
 import GeneratorParameters from '@components/generator-parameters.astro';
@@ -436,14 +438,39 @@ item = ExampleModel.get_by_id('123')
 When running in AWS, `get_table_name()` fetches the table name from AWS AppConfig using the `RUNTIME_CONFIG_APP_ID` environment variable. Projects built with this plugin already have this variable configured automatically. For other Python projects, ensure `RUNTIME_CONFIG_APP_ID` is set in the runtime environment with the AppConfig application ID provisioned by your infrastructure. For more information, see the <Link path="guides/runtime-config">Runtime Configuration guide</Link>.
 :::
 
-### Connection Generators
-
-For specific project types, use the `connection` generator to automatically wire up local development dependencies so DynamoDB Local starts automatically alongside your project, and add the DynamoDB package as a workspace dependency:
-
-- <Link path="guides/connection/py-fast-api-dynamodb">FastAPI → DynamoDB</Link>
-- <Link path="guides/connection/py-agent-dynamodb">Python Agent → DynamoDB</Link>
-- <Link path="guides/connection/py-mcp-server-dynamodb">Python MCP Server → DynamoDB</Link>
-
 ## Deploying your Table
 
 <Snippet name="dynamodb/deploying-table" parentHeading="Deploying your Table" />
+
+## Connections
+
+Use the <Link path="guides/connection">`connection`</Link> generator to integrate this project with others in your workspace. The following connections involve this project:
+
+<CardGrid>
+  <ConnectionCard
+    title="FastAPI to Python DynamoDB"
+    description="Connect a FastAPI to a DynamoDB table"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-fast-api-dynamodb`}
+    source="fastapi"
+    target="dynamodb"
+    targetBadge="python"
+  />
+  <ConnectionCard
+    title="Python Agent to Python DynamoDB"
+    description="Connect a Python Agent to a DynamoDB table"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-agent-dynamodb`}
+    source="strands"
+    sourceBadge="python"
+    target="dynamodb"
+    targetBadge="python"
+  />
+  <ConnectionCard
+    title="Python MCP Server to Python DynamoDB"
+    description="Connect a Python MCP Server to a DynamoDB table"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-mcp-server-dynamodb`}
+    source="mcp"
+    sourceBadge="python"
+    target="dynamodb"
+    targetBadge="python"
+  />
+</CardGrid>

package/docs/guides/py-mcp-server.mdx

@@ -4,7 +4,9 @@ description: Generate a Python Model Context Protocol (MCP) server for providing
 generator: py#mcp-server
 ---
 
-import { FileTree } from '@astrojs/starlight/components';
+import { FileTree, CardGrid } from '@astrojs/starlight/components';
+import Astro from '@astrojs/react';
+import ConnectionCard from '@components/connection-card.astro';
 import RunGenerator from '@components/run-generator.astro';
 import NxCommands from '@components/nx-commands.astro';
 import Link from '@components/link.astro';
@@ -163,3 +165,42 @@ A `docker` target specific to your MCP server is also added, which copies the `D
 
 <Snippet name="mcp/observability" parentHeading="Observability" />
 </OptionFilter>
+
+## Connections
+
+Use the <Link path="guides/connection">`connection`</Link> generator to integrate this project with others in your workspace. The following connections involve this project:
+
+<CardGrid>
+  <ConnectionCard
+    title="TypeScript Agent to MCP"
+    description="Connect a TypeScript Agent to an MCP server"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/ts-agent-mcp`}
+    source="strands"
+    sourceBadge="typescript"
+    target="mcp"
+  />
+  <ConnectionCard
+    title="Python Agent to MCP"
+    description="Connect a Python Agent to an MCP server"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-agent-mcp`}
+    source="strands"
+    sourceBadge="python"
+    target="mcp"
+  />
+  <ConnectionCard
+    title="Python MCP Server to Python DynamoDB"
+    description="Connect a Python MCP Server to a DynamoDB table"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/py-mcp-server-dynamodb`}
+    source="mcp"
+    sourceBadge="python"
+    target="dynamodb"
+    targetBadge="python"
+  />
+  <ConnectionCard
+    title="AgentCore Gateway to MCP Server"
+    description="Aggregate an MCP server behind an AgentCore Gateway"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/agentcore-gateway-mcp`}
+    source="agentcore"
+    target="mcp"
+  />
+</CardGrid>

package/docs/guides/react-website.mdx

@@ -6,7 +6,9 @@ when:
   framework:
     - react
 ---
-import { FileTree, Steps } from '@astrojs/starlight/components';
+import { FileTree, Steps, CardGrid } from '@astrojs/starlight/components';
+import Astro from '@astrojs/react';
+import ConnectionCard from '@components/connection-card.astro';
 import Link from '@components/link.astro';
 import RunGenerator from '@components/run-generator.astro';
 import GeneratorParameters from '@components/generator-parameters.astro';
@@ -430,3 +432,53 @@ provider "aws" {
 </Fragment>
 </Infrastructure>
 
+## Connections
+
+Use the <Link path="guides/connection">`connection`</Link> generator to integrate this project with others in your workspace. The following connections involve this project:
+
+<CardGrid>
+  <ConnectionCard
+    title="React to tRPC"
+    description="Call a tRPC API from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-trpc`}
+    source="react"
+    target="trpc"
+  />
+  <ConnectionCard
+    title="React to FastAPI"
+    description="Call a Python FastAPI from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-fastapi`}
+    source="react"
+    target="fastapi"
+  />
+  <ConnectionCard
+    title="React to Smithy API"
+    description="Call a Smithy API from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-smithy`}
+    source="react"
+    target="smithy"
+  />
+  <ConnectionCard
+    title="React to Python Agent"
+    description="Call a Python Agent from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-py-agent`}
+    source="react"
+    target="strands"
+    targetBadge="python"
+  />
+  <ConnectionCard
+    title="React to TypeScript Agent"
+    description="Call a TypeScript Agent from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-ts-agent`}
+    source="react"
+    target="strands"
+    targetBadge="typescript"
+  />
+  <ConnectionCard
+    title="React to AG-UI Agent"
+    description="Call an Agent exposing the AG-UI protocol from a React website via CopilotKit"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-agui`}
+    source="react"
+    target="copilotkit"
+  />
+</CardGrid>

package/docs/guides/trpc.mdx

@@ -6,7 +6,9 @@ when:
   framework: [trpc]
   infra: [rest-lambda, http-lambda]
 ---
-import { FileTree, Tabs, TabItem } from '@astrojs/starlight/components';
+import { FileTree, Tabs, TabItem, CardGrid } from '@astrojs/starlight/components';
+import Astro from '@astrojs/react';
+import ConnectionCard from '@components/connection-card.astro';
 import Link from '@components/link.astro';
 import RunGenerator from '@components/run-generator.astro';
 import GeneratorParameters from '@components/generator-parameters.astro';
@@ -478,7 +480,7 @@ export interface IIdentityContext {
 
 Note that we define an additional _optional_ property on the context. tRPC manages ensuring that this is defined in procedures which have correctly configured this middleware.
 
-Next, the middleware itself. The generator wires the authorizer to accept ID tokens, so `cognito:username` is the canonical username claim; we fall back to `username` for access tokens in case you reconfigure the authorizer:
+Next, the middleware itself:
 
 ```ts
 import { initTRPC, TRPCError } from '@trpc/server';
@@ -503,7 +505,7 @@ export const createIdentityPlugin = () => {
       | undefined;
 
     const sub = claims?.sub;
-    const username = claims?.['cognito:username'] ?? claims?.username;
+    const username = claims?.username;
 
     if (!sub || !username) {
       throw new TRPCError({
@@ -541,8 +543,8 @@ export const me = publicProcedure
   }));
 ```
 
-:::tip[Verifying the token]
-You don't need `aws-jwt-verify` or any other JWT-verification library here — the API Gateway Cognito User Pools authorizer has already verified the signature, issuer, audience, and expiry by the time your Lambda runs. If any of those checks fail, API Gateway returns `401 Unauthorized` and your handler is never invoked.
+:::tip[No token verification required]
+You don't need `aws-jwt-verify` or any other JWT-verification library here — the API Gateway Cognito User Pools authorizer has already verified the signature, issuer, scopes, and expiry by the time your Lambda runs. If any of those checks fail, API Gateway returns `401 Unauthorized` and your handler is never invoked.
 :::
 </OptionFilter>
 
@@ -817,3 +819,31 @@ If you are calling your API from a React website, consider using the <Link path=
 ## More Information
 
 For more information about tRPC, please refer to the [tRPC documentation](https://trpc.io/docs).
+
+## Connections
+
+Use the <Link path="guides/connection">`connection`</Link> generator to integrate this project with others in your workspace. The following connections involve this project:
+
+<CardGrid>
+  <ConnectionCard
+    title="React to tRPC"
+    description="Call a tRPC API from a React website"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/react-trpc`}
+    source="react"
+    target="trpc"
+  />
+  <ConnectionCard
+    title="tRPC API to Relational Database"
+    description="Connect a tRPC API to an Aurora relational database"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/trpc-rdb`}
+    source="trpc"
+    target="aurora"
+  />
+  <ConnectionCard
+    title="tRPC API to TypeScript DynamoDB"
+    description="Connect a tRPC API to a DynamoDB table"
+    href={`/nx-plugin-for-aws/${Astro.currentLocale || 'en'}/guides/connection/trpc-dynamodb`}
+    source="trpc"
+    target="dynamodb"
+  />
+</CardGrid>