Refactor 3P tool wrappers (#837)

koverholt · joefernandez · web-flow · commit ac968aff44fa · 2025-10-31T09:23:26.000-07:00
* Refactor third-party tools pages

* Remove 3P tool wrapper references

* Update mkdocs.yml - redirect old page locations

---------

Co-authored-by: Joe Fernandez &lt;joefernandez@users.noreply.github.com&gt;
diff --git a/docs/agents/config.md b/docs/agents/config.md
@@ -87,7 +87,7 @@ To create an ADK project for use with Agent Config:
             GOOGLE_GENAI_USE_VERTEXAI=0
             GOOGLE_API_KEY=<your-Google-Gemini-API-key>
 
-        You can get an API key from the Google AI Studio 
+        You can get an API key from the Google AI Studio
         [API Keys](https://aistudio.google.com/app/apikey) page.
 
     1.  For Gemini model access through Google Cloud, add these lines to the file:
@@ -125,7 +125,7 @@ the web interface, command line terminal execution, or API server mode.
 
 To run your Agent Config-defined agent:
 
-1.  In your terminal, navigate to the `my_agent/` directory containing the 
+1.  In your terminal, navigate to the `my_agent/` directory containing the
     `root_agent.yaml` file.
 1.  Type one of the following commands to run your agent:
     -   `adk web` - Run web UI interface for your agent.
@@ -137,7 +137,7 @@ To run your Agent Config-defined agent:
 For more information on the ways to run your agent, see the *Run Your Agent*
 topic in the
 [Quickstart](/adk-docs/get-started/quickstart/#run-your-agent).
-For more information about the ADK command line options, see the 
+For more information about the ADK command line options, see the
 [ADK CLI reference](/adk-docs/api-reference/cli/).
 
 ## Example configs
@@ -222,12 +222,12 @@ For more details, see the full code for this sample in the
 
 ## Deploy agent configs
 
-You can deploy Agent Config agents with 
-[Cloud Run](/adk-docs/deploy/cloud-run/) and 
-[Agent Engine](/adk-docs/deploy/agent-engine/), 
-using the same procedure as code-based agents. For more information on how 
-to prepare and deploy Agent Config-based agents, see the 
-[Cloud Run](/adk-docs/deploy/cloud-run/) and 
+You can deploy Agent Config agents with
+[Cloud Run](/adk-docs/deploy/cloud-run/) and
+[Agent Engine](/adk-docs/deploy/agent-engine/),
+using the same procedure as code-based agents. For more information on how
+to prepare and deploy Agent Config-based agents, see the
+[Cloud Run](/adk-docs/deploy/cloud-run/) and
 [Agent Engine](/adk-docs/deploy/agent-engine/)
 deployment guides.
 
@@ -251,21 +251,19 @@ limitations:
     -   `enterprise_web_search`
     -   `load_web_page`: Requires a fully-qualified path to access web
         pages.
--   **Agent Type Support:** The `LangGraphAgent` and `A2aAgent` types are 
+-   **Agent Type Support:** The `LangGraphAgent` and `A2aAgent` types are
     not yet supported.
     -   `AgentTool`
     -   `LongRunningFunctionTool`
     -   `VertexAiSearchTool`
     -   `MCPToolset`
-    -   `CrewaiTool`
-    -   `LangchainTool`
     -   `ExampleTool`
 
 ## Next steps
 
 For ideas on how and what to build with ADK Agent Configs, see the yaml-based
 agent definitions in the ADK
 [adk-samples](https://github.com/search?q=repo:google/adk-python+path:/%5Econtributing%5C/samples%5C//+root_agent.yaml&type=code)
-repository. For detailed information on the syntax and settings supported by 
+repository. For detailed information on the syntax and settings supported by
 the Agent Config format, see the
 [Agent Config syntax reference](/adk-docs/api-reference/agentconfig/).
diff --git a/docs/community.md b/docs/community.md
@@ -38,7 +38,7 @@ Development Kit community.
     <div class="card-content">
       <div class="type">Video</div>
       <h3>📺 Getting Started with ADK Tools</h3>
-      <p>A guide to building a software bug assistant using tools like MCP, Google Search, and LangChain.</p>
+      <p>A guide to building a software bug assistant using tools like MCP and Google Search.</p>
     </div>
   </a>
 </div>
diff --git a/docs/get-started/about.md b/docs/get-started/about.md
@@ -88,8 +88,7 @@ agentic applications:
    generated reports during their execution.
 9. **Extensibility and Interoperability:** ADK promotes an open
    ecosystem. While providing core tools, it allows developers to easily
-   integrate and reuse tools from other popular agent frameworks including
-   LangChain and CrewAI.
+   integrate and reuse third-party tools and data connectors.
 10. **State and Memory Management:** Automatically handles short-term
     conversational memory (`State` within a `Session`) managed by the
     `SessionService`. Provides integration points for longer-term `Memory`
diff --git a/docs/index.md b/docs/index.md
@@ -83,8 +83,8 @@ from simple tasks to complex workflows.
     ---
 
     Equip agents with diverse capabilities: use pre-built tools (Search, Code
-    Exec), create custom functions, integrate 3rd-party libraries (LangChain,
-    CrewAI), or even use other agents as tools.
+    Exec), create custom functions, integrate 3rd-party libraries, or even use
+    other agents as tools.
 
     [**Browse tools**](tools/index.md)
 
diff --git a/docs/tools-custom/index.md b/docs/tools-custom/index.md
@@ -66,7 +66,6 @@ ADK offers flexibility by supporting several types of tools:
 2. **[Built-in Tools](../tools/built-in-tools.md):** Ready-to-use tools provided by the framework for common tasks.
         Examples: Google Search, Code Execution, Retrieval-Augmented Generation (RAG).
 3. **Third-Party Tools:** Integrate tools seamlessly from popular external libraries.
-        Examples: [LangChain Tools](/adk-docs/tools/third-party/langchain/), [CrewAI Tools](/adk-docs/tools/third-party/crewai/).
 
 Navigate to the respective documentation pages linked above for detailed information and examples for each tool type.
 
diff --git a/docs/tools/index.md b/docs/tools/index.md
@@ -165,18 +165,6 @@ Check out the following pre-built tools that you can use with ADK agents:
 
 </div>
 
-## Integrate with existing tools
-
-ADK provides tool integrations and wrappers for existing tool ecosystems
-to help you extend the capabilities of your agents and workflows:
-
-*   **[LangChain Tools](/adk-docs/tools/third-party/langchain/)**:
-    Integrate tools from the LangChain ecosystem.
-*   **[CrewAI Tools](/adk-docs/tools/third-party/crewai/)**:
-    Integrate tools from the CrewAI library.
-*   **[Agentic UI](/adk-docs/tools/third-party/ag-ui/)**:
-    Use a rich, alternative web interface for ADK workflows.
-
 ## Build your tools
 
 If the above tools don't meet your needs, you can build tools for your ADK
diff --git a/docs/tools/mcp-tools.md b/docs/tools/mcp-tools.md
@@ -794,7 +794,6 @@ When working with MCP and ADK, keep these points in mind:
 
     * ADK Tools (BaseTool, FunctionTool, AgentTool, etc.) are Python objects designed for direct use within the ADK's LlmAgent and Runner.
     * MCP Tools are capabilities exposed by an MCP Server according to the protocol's schema. MCPToolset makes these look like ADK tools to an LlmAgent.
-    * Langchain/CrewAI Tools are specific implementations within those libraries, often simple functions or classes, lacking the server/protocol structure of MCP. ADK offers wrappers (LangchainTool, CrewaiTool) for some interoperability.
 
 * **Asynchronous nature:** Both ADK and the MCP Python library are heavily based on the asyncio Python library. Tool implementations and server handlers should generally be async functions.
 
@@ -978,9 +977,9 @@ def create_mcp_server():
 def main(port: int = 8080, json_response: bool = False):
     """Main server function."""
     logging.basicConfig(level=logging.INFO)
-    
+
     app = create_mcp_server()
-    
+
     # Create session manager with stateless mode for scalability
     session_manager = StreamableHTTPSessionManager(
         app=app,
@@ -1051,7 +1050,7 @@ spec:
         env:
         - name: MCP_SERVER_URL
           value: "http://localhost:8081"
-      
+
       # MCP server sidecar
       - name: mcp-server
         image: your-mcp-server:latest
@@ -1066,7 +1065,7 @@ spec:
 - **Cons:** Process overhead, not suitable for high-scale deployments
 - **Best for:** Development, single-tenant deployments, simple MCP servers
 
-#### SSE/HTTP Connections  
+#### SSE/HTTP Connections
 - **Pros:** Network-based, scalable, can handle multiple clients
 - **Cons:** Requires network infrastructure, authentication complexity
 - **Best for:** Production deployments, multi-tenant systems, external MCP services
@@ -1175,7 +1174,7 @@ MCPToolset(
    ```python
    # Test remote MCP connectivity
    import aiohttp
-   
+
    async def test_mcp_connection():
        async with aiohttp.ClientSession() as session:
            async with session.get('https://your-mcp-server.com/health') as resp:
@@ -1191,4 +1190,4 @@ MCPToolset(
 
 * [Model Context Protocol Documentation](https://modelcontextprotocol.io/ )
 * [MCP Specification](https://modelcontextprotocol.io/specification/)
-* [MCP Python SDK & Examples](https://github.com/modelcontextprotocol/)
+* [MCP Python SDK & Examples](https://github.com/modelcontextprotocol/)
diff --git a/docs/tools/third-party/crewai.md b/docs/tools/third-party/crewai.md
diff --git a/docs/tools/third-party/index.md b/docs/tools/third-party/index.md
@@ -35,15 +35,3 @@ Check out the following third-party tools that you can use with ADK agents:
   </a>
 
 </div>
-
-## Integrate with existing tools
-
-ADK provides tool integrations and wrappers for existing tool ecosystems
-to help you extend the capabilities of your agents and workflows:
-
-*   **[LangChain Tools](/adk-docs/tools/third-party/langchain/)**:
-    Integrate tools from the LangChain ecosystem.
-*   **[CrewAI Tools](/adk-docs/tools/third-party/crewai/)**:
-    Integrate tools from the CrewAI library.
-*   **[Agentic UI](/adk-docs/tools/third-party/ag-ui/)**:
-    Use a rich, alternative web interface for ADK workflows.
diff --git a/docs/tools/third-party/langchain.md b/docs/tools/third-party/langchain.md
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -120,6 +120,8 @@ plugins:
         'tools/third-party/openapi-tools.md': tools-custom/openapi-tools.md
         'tools/openapi-tools.md': tools-custom/openapi-tools.md
         'tutorials/ag-ui.md': tools/third-party/ag-ui.md
+        'tools/third-party/langchain.md': tools/index.md 
+        'tools/third-party/crewai.md':  tools/index.md
 
 # Navigation
 nav:
@@ -166,8 +168,6 @@ nav:
       - Firecrawl: tools/third-party/firecrawl.md
       - GitHub: tools/third-party/github.md
       - Hugging Face: tools/third-party/hugging-face.md
-      - LangChain tools: tools/third-party/langchain.md
-      - CrewAI tools: tools/third-party/crewai.md
       - Agentic UI (AG-UI): tools/third-party/ag-ui.md
   - Custom Tools:
     - tools-custom/index.md
diff --git a/tools/feature-matrix/start.md b/tools/feature-matrix/start.md
@@ -1,6 +1,6 @@
 ## ADK Features
 
-!!! note: 
+!!! note:
 This content is autogenerated by Gemini, based on our documentation.  It is a best effort to generate a feature matrix, but may not be 100% accurate as features can outpace documentation, or Gemini might inaccurately generate content.
 
 ## Feature Support Matrix
@@ -26,7 +26,6 @@ The following matrix shows which ADK features are currently supported in each la
 | | **Built-in: Vertex AI Search** | [Supported](https://google.github.io/adk-docs/tools/built-in-tools/#vertex-ai-search) | Not Supported |
 | | **Built-in: BigQuery, Spanner, Bigtable** | [Supported](https://google.github.io/adk-docs/tools/built-in-tools/#bigquery) | Not Supported |
 | | **Google Cloud Tools (API Hub, etc.)** | [Supported](https://google.github.io/adk-docs/tools/google-cloud-tools/#apigee-api-hub-tools) | Not Supported |
-| | **Third-Party Tools (LangChain, CrewAI)** | [Supported](https://google.github.io/adk-docs/tools/third-party-tools/#1-using-langchain-tools) | Not Supported |
 | | **MCP Tools** | [Supported](https://google.github.io/adk-docs/tools/mcp-tools/#example-1-file-system-mcp-server) | [Supported](https://google.github.io/adk-docs/tools/mcp-tools/#example-1-file-system-mcp-server) |
 | | **Tool Confirmation** | [Supported](https://google.github.io/adk-docs/tools/confirmation/#boolean-confirmation) | Not Supported |
 | | **Tool Authentication** | [Supported](https://google.github.io/adk-docs/tools/authentication/#1-configuring-tools-with-authentication) | Not Supported |
@@ -66,7 +65,6 @@ Based on the documentation, ADK delivers a comprehensive set of features for bui
 *   **Agents-as-a-Tool**: Use an entire agent as a callable tool within another agent.
 *   **Built-in Tools**: Leverage pre-built capabilities like Google Search, Vertex AI Search, and secure code execution.
 *   **Google Cloud Tools**: Seamlessly connect to Google Cloud services like API Hub, Application Integration, and databases via MCP Toolbox.
-*   **Third-Party Tools**: Integrate tools from popular frameworks like LangChain and CrewAI.
 *   **MCP (Model Context Protocol) Tools**: Use and expose tools via the open MCP standard.
 *   **Tool Confirmation**: Implement human-in-the-loop workflows by requiring user confirmation before a tool executes.
 *   **Tool Authentication**: Securely manage credentials for tools that access protected APIs.
@@ -87,4 +85,3 @@ Based on the documentation, ADK delivers a comprehensive set of features for bui
 *   **Observability & Logging**: Gain deep insights into agent behavior with detailed logging and integrations with observability platforms like AgentOps, Arize AX, Cloud Trace, and Weave.
 *   **Deployment**: Deploy your agents to a variety of environments, including serverless (Cloud Run), Kubernetes (GKE), and the fully managed Vertex AI Agent Engine.
 *   **Agent2Agent (A2A) Protocol**: Build distributed, multi-agent systems where agents running as separate services can communicate and collaborate using the open A2A standard.
-
