mcp-use 1.3.8__tar.gz → 1.3.9__tar.gz

{mcp_use-1.3.8 → mcp_use-1.3.9}/.github/release-drafter.yml

@@ -1,5 +1,5 @@
-name-template: 'Release v$RESOLVED_VERSION 🌈'
-tag-template: 'Releasev$RESOLVED_VERSION'
+name-template: '$RESOLVED_VERSION 🌈'
+tag-template: '$RESOLVED_VERSION'
 categories:
   - title: '🚀 Features'
     labels:

{mcp_use-1.3.8 → mcp_use-1.3.9}/.github/workflows/tests.yml

@@ -77,7 +77,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        primitive: [sampling, tools, resources, prompts, elicitation]
+        primitive: [sampling, tools, resources, prompts, elicitation, notifications]
     steps:
       - uses: actions/checkout@v3
       - name: Set up Python 3.11

{mcp_use-1.3.8 → mcp_use-1.3.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-use
-Version: 1.3.8
+Version: 1.3.9
 Summary: MCP Library for LLMs
 Author-email: Pietro Zullo <pietro.zullo@gmail.com>
 License: MIT
@@ -46,25 +46,30 @@ Description-Content-Type: text/markdown
 <div align="center">
 <div align="center" style="margin: 0 auto; max-width: 80%;">
   <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="static/logo_white.svg">
-    <source media="(prefers-color-scheme: light)" srcset="static/logo_black.svg">
-    <img alt="mcp use logo" src="./static/logo-white.svg" width="80%" style="margin: 20px auto;">
+    <source media="(prefers-color-scheme: dark)" srcset="static/logo-gh.jpg">
+    <source media="(prefers-color-scheme: light)" srcset="static/logo-gh.jpg">
+    <img alt="mcp use logo" src="./static/logo-gh.jpg" width="80%" style="margin: 20px auto;">
   </picture>
 </div>
 
 <br>
 
-# Connect any LLM to any MCP server
+# Create MCP Clients and Agents
 
+<p align="center">
+<a href="https://www.producthunt.com/products/mcp-use?embed=true&utm_source=badge-featured&utm_medium=badge&utm_source=badge-mcp&#0045;use" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1002629&theme=neutral&t=1754609432704" alt="mcp&#0045;use - Open&#0032;source&#0032;SDK&#0032;and&#0032;infra&#0032;for&#0032;MCP&#0032;servers&#0032;&#0038;&#0032;agents | Product Hunt" style="width: 150px; height: 32px;" width="150" height="32" /></a>
+</p>
 <p align="center">
     <a href="https://github.com/pietrozullo/mcp-use/stargazers" alt="GitHub stars">
         <img src="https://img.shields.io/github/stars/pietrozullo/mcp-use?style=social" /></a>
+    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Downloads">
+        <img src="https://static.pepy.tech/badge/mcp-use" /></a>
     <a href="https://pypi.org/project/mcp_use/" alt="PyPI Version">
         <img src="https://img.shields.io/pypi/v/mcp_use.svg"/></a>
+    <a href="https://github.com/mcp-use/mcp-use-ts" alt="TypeScript">
+      <img src="https://img.shields.io/badge/TypeScript-mcp--use-3178C6?logo=typescript&logoColor=white" /></a>
     <a href="https://github.com/pietrozullo/mcp-use/blob/main/LICENSE" alt="License">
         <img src="https://img.shields.io/github/license/pietrozullo/mcp-use" /></a>
-    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Downloads">
-        <img src="https://static.pepy.tech/badge/mcp-use" /></a>
     <a href="https://docs.mcp-use.com" alt="Documentation">
         <img src="https://img.shields.io/badge/docs-mcp--use.com-blue" /></a>
     <a href="https://mcp-use.com" alt="Website">
@@ -88,10 +93,10 @@ Description-Content-Type: text/markdown
 - Visit the [mcp-use docs](https://docs.mcp-use.com/) to get started with mcp-use library
 - For the TypeScript version, visit [mcp-use-ts](https://github.com/mcp-use/mcp-use-ts)
 
-| Supports  | |
-| :--- | :--- |
+| Supports       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| :------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | **Primitives** | [![Tools](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-tools&label=Tools&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Resources](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-resources&label=Resources&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Prompts](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-prompts&label=Prompts&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Sampling](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-sampling&label=Sampling&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Elicitation](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-elicitation&label=Elicitation&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) |
-| **Transports** | [![Stdio](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-stdio&label=Stdio&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![SSE](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-sse&label=SSE&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Streamable HTTP](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-streamableHttp&label=Streamable%20HTTP&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) |
+| **Transports** | [![Stdio](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-stdio&label=Stdio&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![SSE](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-sse&label=SSE&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Streamable HTTP](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-streamableHttp&label=Streamable%20HTTP&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml)                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 
 ## Features
 
@@ -417,29 +422,7 @@ if __name__ == "__main__":
     asyncio.run(run_blender_example())
 ```
 
-# Configuration File Support
-
-MCP-Use supports initialization from configuration files, making it easy to manage and switch between different MCP server setups:
-
-```python
-import asyncio
-from mcp_use import create_session_from_config
-
-async def main():
-    # Create an MCP session from a config file
-    session = create_session_from_config("mcp-config.json")
-
-    # Initialize the session
-    await session.initialize()
-
-    # Use the session...
-
-    # Disconnect when done
-    await session.disconnect()
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
+# Configuration Support
 
 ## HTTP Connection Example
 
@@ -695,6 +678,47 @@ The `SandboxOptions` type provides configuration for the sandbox environment:
 - **Consistent environment**: Ensure consistent behavior across different systems
 - **Resource efficiency**: Offload resource-intensive tasks to cloud infrastructure
 
+# Direct Tool Calls (Without LLM)
+
+You can call MCP server tools directly without an LLM when you need programmatic control:
+
+```python
+import asyncio
+from mcp_use import MCPClient
+
+async def call_tool_example():
+    config = {
+        "mcpServers": {
+            "everything": {
+                "command": "npx",
+                "args": ["-y", "@modelcontextprotocol/server-everything"],
+            }
+        }
+    }
+
+    client = MCPClient.from_dict(config)
+
+    try:
+        await client.create_all_sessions()
+        session = client.get_session("everything")
+
+        # Call tool directly
+        result = await session.call_tool(
+            name="add",
+            arguments={"a": 1, "b": 2}
+        )
+
+        print(f"Result: {result.content[0].text}")  # Output: 3
+
+    finally:
+        await client.close_all_sessions()
+
+if __name__ == "__main__":
+    asyncio.run(call_tool_example())
+```
+
+See the complete example: [examples/direct_tool_call.py](examples/direct_tool_call.py)
+
 # Build a Custom Agent:
 
 You can also build your own custom agent using the LangChain adapter:
@@ -813,23 +837,27 @@ Thanks to all our amazing contributors!
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/38653995?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/patchy631/ai-engineering-hub"><strong>patchy631/ai-engineering-hub</strong></a></td>
-    <td>⭐ 15189</td>
+    <td>⭐ 15920</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/170207473?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/tavily-ai/meeting-prep-agent"><strong>tavily-ai/meeting-prep-agent</strong></a></td>
     <td>⭐ 129</td>
   </tr>
   <tr>
-    <td><img src="https://avatars.githubusercontent.com/u/187057607?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/hud-evals/hud-sdk"><strong>hud-evals/hud-sdk</strong></a></td>
-    <td>⭐ 75</td>
+    <td><img src="https://avatars.githubusercontent.com/u/164294848?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/buildfastwithai/gen-ai-experiments"><strong>buildfastwithai/gen-ai-experiments</strong></a></td>
+    <td>⭐ 93</td>
+  </tr>
+  <tr>
+    <td><img src="https://avatars.githubusercontent.com/u/187057607?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/hud-evals/hud-python"><strong>hud-evals/hud-python</strong></a></td>
+    <td>⭐ 76</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/20041231?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/krishnaik06/MCP-CRASH-Course"><strong>krishnaik06/MCP-CRASH-Course</strong></a></td>
-    <td>⭐ 58</td>
+    <td>⭐ 61</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/54944174?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/larksuite/lark-samples"><strong>larksuite/lark-samples</strong></a></td>
-    <td>⭐ 31</td>
+    <td>⭐ 35</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/892404?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/truemagic-coder/solana-agent-app"><strong>truemagic-coder/solana-agent-app</strong></a></td>
@@ -845,11 +873,7 @@ Thanks to all our amazing contributors!
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/100749943?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/Deniscartin/mcp-cli"><strong>Deniscartin/mcp-cli</strong></a></td>
-    <td>⭐ 18</td>
-  </tr>
-  <tr>
-    <td><img src="https://avatars.githubusercontent.com/u/6688805?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/innovaccer/Healthcare-MCP"><strong>innovaccer/Healthcare-MCP</strong></a></td>
-    <td>⭐ 15</td>
+    <td>⭐ 19</td>
   </tr>
 </table>
 

{mcp_use-1.3.8 → mcp_use-1.3.9}/README.md

@@ -1,25 +1,30 @@
 <div align="center">
 <div align="center" style="margin: 0 auto; max-width: 80%;">
   <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="static/logo_white.svg">
-    <source media="(prefers-color-scheme: light)" srcset="static/logo_black.svg">
-    <img alt="mcp use logo" src="./static/logo-white.svg" width="80%" style="margin: 20px auto;">
+    <source media="(prefers-color-scheme: dark)" srcset="static/logo-gh.jpg">
+    <source media="(prefers-color-scheme: light)" srcset="static/logo-gh.jpg">
+    <img alt="mcp use logo" src="./static/logo-gh.jpg" width="80%" style="margin: 20px auto;">
   </picture>
 </div>
 
 <br>
 
-# Connect any LLM to any MCP server
+# Create MCP Clients and Agents
 
+<p align="center">
+<a href="https://www.producthunt.com/products/mcp-use?embed=true&utm_source=badge-featured&utm_medium=badge&utm_source=badge-mcp&#0045;use" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/featured.svg?post_id=1002629&theme=neutral&t=1754609432704" alt="mcp&#0045;use - Open&#0032;source&#0032;SDK&#0032;and&#0032;infra&#0032;for&#0032;MCP&#0032;servers&#0032;&#0038;&#0032;agents | Product Hunt" style="width: 150px; height: 32px;" width="150" height="32" /></a>
+</p>
 <p align="center">
     <a href="https://github.com/pietrozullo/mcp-use/stargazers" alt="GitHub stars">
         <img src="https://img.shields.io/github/stars/pietrozullo/mcp-use?style=social" /></a>
+    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Downloads">
+        <img src="https://static.pepy.tech/badge/mcp-use" /></a>
     <a href="https://pypi.org/project/mcp_use/" alt="PyPI Version">
         <img src="https://img.shields.io/pypi/v/mcp_use.svg"/></a>
+    <a href="https://github.com/mcp-use/mcp-use-ts" alt="TypeScript">
+      <img src="https://img.shields.io/badge/TypeScript-mcp--use-3178C6?logo=typescript&logoColor=white" /></a>
     <a href="https://github.com/pietrozullo/mcp-use/blob/main/LICENSE" alt="License">
         <img src="https://img.shields.io/github/license/pietrozullo/mcp-use" /></a>
-    <a href="https://pypi.org/project/mcp_use/" alt="PyPI Downloads">
-        <img src="https://static.pepy.tech/badge/mcp-use" /></a>
     <a href="https://docs.mcp-use.com" alt="Documentation">
         <img src="https://img.shields.io/badge/docs-mcp--use.com-blue" /></a>
     <a href="https://mcp-use.com" alt="Website">
@@ -43,10 +48,10 @@
 - Visit the [mcp-use docs](https://docs.mcp-use.com/) to get started with mcp-use library
 - For the TypeScript version, visit [mcp-use-ts](https://github.com/mcp-use/mcp-use-ts)
 
-| Supports  | |
-| :--- | :--- |
+| Supports       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| :------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | **Primitives** | [![Tools](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-tools&label=Tools&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Resources](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-resources&label=Resources&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Prompts](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-prompts&label=Prompts&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Sampling](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-sampling&label=Sampling&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Elicitation](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=primitive-elicitation&label=Elicitation&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) |
-| **Transports** | [![Stdio](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-stdio&label=Stdio&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![SSE](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-sse&label=SSE&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Streamable HTTP](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-streamableHttp&label=Streamable%20HTTP&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) |
+| **Transports** | [![Stdio](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-stdio&label=Stdio&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![SSE](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-sse&label=SSE&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml) [![Streamable HTTP](https://img.shields.io/github/actions/workflow/status/pietrozullo/mcp-use/tests.yml?job=transport-streamableHttp&label=Streamable%20HTTP&style=flat)](https://github.com/pietrozullo/mcp-use/actions/workflows/tests.yml)                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
 
 ## Features
 
@@ -372,29 +377,7 @@ if __name__ == "__main__":
     asyncio.run(run_blender_example())
 ```
 
-# Configuration File Support
-
-MCP-Use supports initialization from configuration files, making it easy to manage and switch between different MCP server setups:
-
-```python
-import asyncio
-from mcp_use import create_session_from_config
-
-async def main():
-    # Create an MCP session from a config file
-    session = create_session_from_config("mcp-config.json")
-
-    # Initialize the session
-    await session.initialize()
-
-    # Use the session...
-
-    # Disconnect when done
-    await session.disconnect()
-
-if __name__ == "__main__":
-    asyncio.run(main())
-```
+# Configuration Support
 
 ## HTTP Connection Example
 
@@ -650,6 +633,47 @@ The `SandboxOptions` type provides configuration for the sandbox environment:
 - **Consistent environment**: Ensure consistent behavior across different systems
 - **Resource efficiency**: Offload resource-intensive tasks to cloud infrastructure
 
+# Direct Tool Calls (Without LLM)
+
+You can call MCP server tools directly without an LLM when you need programmatic control:
+
+```python
+import asyncio
+from mcp_use import MCPClient
+
+async def call_tool_example():
+    config = {
+        "mcpServers": {
+            "everything": {
+                "command": "npx",
+                "args": ["-y", "@modelcontextprotocol/server-everything"],
+            }
+        }
+    }
+
+    client = MCPClient.from_dict(config)
+
+    try:
+        await client.create_all_sessions()
+        session = client.get_session("everything")
+
+        # Call tool directly
+        result = await session.call_tool(
+            name="add",
+            arguments={"a": 1, "b": 2}
+        )
+
+        print(f"Result: {result.content[0].text}")  # Output: 3
+
+    finally:
+        await client.close_all_sessions()
+
+if __name__ == "__main__":
+    asyncio.run(call_tool_example())
+```
+
+See the complete example: [examples/direct_tool_call.py](examples/direct_tool_call.py)
+
 # Build a Custom Agent:
 
 You can also build your own custom agent using the LangChain adapter:
@@ -768,23 +792,27 @@ Thanks to all our amazing contributors!
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/38653995?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/patchy631/ai-engineering-hub"><strong>patchy631/ai-engineering-hub</strong></a></td>
-    <td>⭐ 15189</td>
+    <td>⭐ 15920</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/170207473?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/tavily-ai/meeting-prep-agent"><strong>tavily-ai/meeting-prep-agent</strong></a></td>
     <td>⭐ 129</td>
   </tr>
   <tr>
-    <td><img src="https://avatars.githubusercontent.com/u/187057607?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/hud-evals/hud-sdk"><strong>hud-evals/hud-sdk</strong></a></td>
-    <td>⭐ 75</td>
+    <td><img src="https://avatars.githubusercontent.com/u/164294848?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/buildfastwithai/gen-ai-experiments"><strong>buildfastwithai/gen-ai-experiments</strong></a></td>
+    <td>⭐ 93</td>
+  </tr>
+  <tr>
+    <td><img src="https://avatars.githubusercontent.com/u/187057607?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/hud-evals/hud-python"><strong>hud-evals/hud-python</strong></a></td>
+    <td>⭐ 76</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/20041231?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/krishnaik06/MCP-CRASH-Course"><strong>krishnaik06/MCP-CRASH-Course</strong></a></td>
-    <td>⭐ 58</td>
+    <td>⭐ 61</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/54944174?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/larksuite/lark-samples"><strong>larksuite/lark-samples</strong></a></td>
-    <td>⭐ 31</td>
+    <td>⭐ 35</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/892404?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/truemagic-coder/solana-agent-app"><strong>truemagic-coder/solana-agent-app</strong></a></td>
@@ -800,11 +828,7 @@ Thanks to all our amazing contributors!
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/100749943?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/Deniscartin/mcp-cli"><strong>Deniscartin/mcp-cli</strong></a></td>
-    <td>⭐ 18</td>
-  </tr>
-  <tr>
-    <td><img src="https://avatars.githubusercontent.com/u/6688805?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/innovaccer/Healthcare-MCP"><strong>innovaccer/Healthcare-MCP</strong></a></td>
-    <td>⭐ 15</td>
+    <td>⭐ 19</td>
   </tr>
 </table>
 

{mcp_use-1.3.8 → mcp_use-1.3.9}/docs/api-reference/mcpagent.mdx

@@ -48,7 +48,8 @@ async def run(
     max_steps: int | None = None,
     manage_connector: bool = True,
     external_history: list[BaseMessage] | None = None,
-) -> str:
+    output_schema: type[T] | None = None,
+) -> str | T:
 ```
 
 Run agent execution and return the final result. Uses the streaming implementation internally.
@@ -58,17 +59,34 @@ Run agent execution and return the final result. Uses the streaming implementati
 - `max_steps` (int, optional): Maximum number of steps to take
 - `manage_connector` (bool): Whether to handle connector lifecycle
 - `external_history` (list[BaseMessage], optional): External conversation history
+- `output_schema` (type[T], optional): Pydantic model for structured output. If provided, the agent will return an instance of this model.
 
 **Returns:**
-- `str`: The final result
+- `str` | `T`: The final result as a string, or a Pydantic model instance if `output_schema` is provided.
 
-**Example:**
+**Examples:**
 
+**Basic Usage**
 ```python
 result = await agent.run("What's the weather like?")
 print(result)
 ```
 
+**Structured Output**
+```python
+from pydantic import BaseModel, Field
+
+class WeatherInfo(BaseModel):
+    temperature: float = Field(description="Temperature in Celsius")
+    condition: str = Field(description="Weather condition")
+
+weather: WeatherInfo = await agent.run(
+    "What's the weather like in London?",
+    output_schema=WeatherInfo
+)
+print(f"Temperature: {weather.temperature}°C, Condition: {weather.condition}")
+```
+
 ## astream
 
 ```python
@@ -106,7 +124,9 @@ async for chunk in agent.astream("hello"):
 | `run()` | Simple execution | Final result only | Complete |
 | `astream()` | Real-time chat interfaces | Streaming chunks | Token-level |
 
-## Configuration Methods
+## Conversation Memory
+
+Methods for managing the agent's conversation history.
 
 ### get_conversation_history
 
@@ -114,7 +134,10 @@ async for chunk in agent.astream("hello"):
 def get_conversation_history() -> list[BaseMessage]:
 ```
 
-Get the current conversation history.
+Retrieves the current conversation history, which is a list of LangChain `BaseMessage` objects. This is useful for inspecting the agent's memory or for passing it to another agent.
+
+**Returns:**
+- `list[BaseMessage]`: The list of messages in the conversation history.
 
 ### clear_conversation_history
 
@@ -122,7 +145,24 @@ Get the current conversation history.
 def clear_conversation_history() -> None:
 ```
 
-Clear the conversation history.
+Clears the agent's conversation history. This is useful for starting a new conversation without creating a new agent instance. The system message is preserved.
+
+**Example:**
+```python
+# Run a query, which populates the history
+await agent.run("What is the capital of France?")
+
+# Clear the history
+agent.clear_conversation_history()
+
+# The next query will not have the context of the first one
+await agent.run("What was the last question I asked?")
+# Assistant: I'm sorry, I don't have access to our previous conversation.
+```
+
+## Agent Management
+
+Methods for managing the agent's lifecycle and configuration.
 
 ### set_system_message
 

{mcp_use-1.3.8 → mcp_use-1.3.9}/docs/client/client-configuration.mdx

@@ -100,115 +100,11 @@ You can configure multiple MCP servers in a single configuration file, allowing
 
 For a complete example of using multiple servers, see the [multi-server example](https://github.com/mcp-use/mcp-use/blob/main/examples/multi_server_example.py) in our repository.
 
-### Working with Multiple Servers
-
-The `MCPClient` can be configured with multiple MCP servers, allowing your agent to access tools from different sources. This capability enables complex workflows spanning various domains (e.g., web browsing and API interaction).
-
-When an `MCPClient` with multiple servers is passed to an `MCPAgent`, the agent gains access to tools from all configured servers. By default, you might need to guide the agent or explicitly specify which server to use for a given task using the `server_name` parameter in the `agent.run()` method.
-
-```python
-# Assuming MCPClient is initialized with the multi_server_config.json
-client = MCPClient.from_config_file("multi_server_config.json")
-agent = MCPAgent(llm=llm, client=client) # Server manager not enabled by default
-
-# Manually specify the server if needed
-result = await agent.run(
-    "Search for Airbnb listings in Barcelona",
-    server_name="airbnb"
-)
-```
-
-
-## Sandboxed Execution
-
-mcp_use supports running MCP servers in a sandboxed cloud environment using E2B. This is useful when you want to run MCP servers without having to install their dependencies locally.
-
-### Installation
-
-To use sandboxed execution, you need to install the E2B dependency:
-
-```bash
-# Install mcp-use with E2B support
-pip install "mcp-use[e2b]"
-
-# Or install the dependency directly
-pip install e2b-code-interpreter
-```
-
-You'll also need an E2B API key. You can sign up at [e2b.dev](https://e2b.dev) to get your API key.
-
-### Configuration Example
-
-To enable sandboxed execution, use the sandbox parameter when creating the MCPClient:
-
-```python
-from mcp_use import MCPClient
-from mcp_use.types.sandbox import SandboxOptions
-
-# Define sandbox options
-sandbox_options: SandboxOptions = {
-    "api_key": "your_e2b_api_key",  # Or use E2B_API_KEY environment variable
-    "sandbox_template_id": "code-interpreter-v1",
-    "supergateway_command": "npx -y supergateway"  # Optional, this is the default
-}
-
-# Create client with sandboxed execution enabled
-client = MCPClient.from_dict(
-    {
-        "mcpServers": {
-            "command_line": {
-                "command": "npx",
-                "args": ["-y", "@modelcontextprotocol/server-everything"]
-            }
-        }
-    },
-    sandbox=True,
-    sandbox_options=sandbox_options
-)
-```
-
-### Available Sandbox Options
-
-The `SandboxOptions` type provides the following configuration options:
-
-| Option                 | Description                                                                              | Default               |
-| ---------------------- | ---------------------------------------------------------------------------------------- | --------------------- |
-| `api_key`              | E2B API key. Required - can be provided directly or via E2B_API_KEY environment variable | None                  |
-| `sandbox_template_id`  | Template ID for the sandbox environment                                                  | "base"                |
-| `supergateway_command` | Command to run supergateway                                                              | "npx -y supergateway" |
-
-### E2B API Key
-
-To use sandboxed execution, you need an E2B API key. You can provide it in two ways:
-
-1. Directly in the sandbox options:
-
-   ```python
-   sandbox_options = {"api_key": "your_e2b_api_key"}
-   ```
-
-2. Through the environment variable:
-   ```bash
-   # In your .env file or environment
-   E2B_API_KEY=your_e2b_api_key
-   ```
-
-For more details on connection types and sandbox configuration, see the [Connection Types](./connection-types) guide.
 
 ## Client Creation Methods
 
 There are several ways to create an MCPClient:
 
-### From Configuration File
-
-Load configuration from a JSON file:
-
-```python
-from mcp_use import MCPClient
-
-client = MCPClient.from_config_file("config.json")
-```
-
 ### From Dictionary
 
 Create configuration programmatically:
@@ -226,9 +122,20 @@ config = {
     }
 }
 
-client = MCPClient.from_dict(config)
+client = MCPClient(config)
 ```
 
+### From Configuration File
+
+Load configuration from a JSON file:
+
+```python
+from mcp_use import MCPClient
+
+client = MCPClient.from_config_file("config.json")
+```
+
+
 ### With Sandbox Options
 
 Enable sandboxed execution: