mcp-use 1.1.4__tar.gz → 1.2.5__tar.gz

{mcp_use-1.1.4 → mcp_use-1.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-use
-Version: 1.1.4
+Version: 1.2.5
 Summary: MCP Library for LLMs
 Author-email: Pietro Zullo <pietro.zullo@gmail.com>
 License: MIT
@@ -41,9 +41,9 @@ Description-Content-Type: text/markdown
   <img alt="" src="./static/image.jpg"  width="full">
 </picture>
 
-<h1 align="center">Open Source MCP CLient Library </h1>
+<h1 align="center">Unified MCP Client Library </h1>
 
-[![](https://img.shields.io/pypi/dd/mcp_use.svg)](https://pypi.org/project/mcp_use/)
+[![](https://img.shields.io/pypi/dw/mcp_use.svg)](https://pypi.org/project/mcp_use/)
 [![PyPI Downloads](https://img.shields.io/pypi/dm/mcp_use.svg)](https://pypi.org/project/mcp_use/)
 [![PyPI Version](https://img.shields.io/pypi/v/mcp_use.svg)](https://pypi.org/project/mcp_use/)
 [![Python Versions](https://img.shields.io/pypi/pyversions/mcp_use.svg)](https://pypi.org/project/mcp_use/)
@@ -51,8 +51,9 @@ Description-Content-Type: text/markdown
 [![License](https://img.shields.io/github/license/pietrozullo/mcp-use)](https://github.com/pietrozullo/mcp-use/blob/main/LICENSE)
 [![Code style: Ruff](https://img.shields.io/badge/code%20style-ruff-000000.svg)](https://github.com/astral-sh/ruff)
 [![GitHub stars](https://img.shields.io/github/stars/pietrozullo/mcp-use?style=social)](https://github.com/pietrozullo/mcp-use/stargazers)
+[![Twitter Follow](https://img.shields.io/twitter/follow/Pietro?style=social)](https://x.com/pietrozullo)
 
-🌐 MCP-Use is the open source way to connect any LLM to MCP tools and build custom agents that have tool access, without using closed source or application clients.
+🌐 MCP-Use is the open source way to connect **any LLM to any MCP server** and build custom agents that have tool access, without using closed source or application clients.
 
 💡 Let developers easily connect any LLM to tools like web browsing, file operations, and more.
 
@@ -65,6 +66,7 @@ Description-Content-Type: text/markdown
 | 🔄 **Ease of use** | Create your first MCP capable agent you need only 6 lines of code |
 | 🤖 **LLM Flexibility** | Works with any langchain supported LLM that supports tool calling (OpenAI, Anthropic, Groq, LLama etc.) |
 | 🌐 **HTTP Support** | Direct connection to MCP servers running on specific HTTP ports |
+| ⚙️ **Dynamic Server Selection** | Agents can dynamically choose the most appropriate MCP server for a given task from the available pool |
 | 🧩 **Multi-Server Support** | Use multiple MCP servers simultaneously in a single agent |
 | 🛡️ **Tool Restrictions** | Restrict potentially dangerous tools like file system or network access |
 
@@ -179,7 +181,6 @@ Example configuration file (`browser_mcp.json`):
 
 For other settings, models, and more, check out the documentation.
 
-# Features
 
 # Example Use Cases
 
@@ -389,7 +390,7 @@ This example demonstrates how to connect to an MCP server running on a specific
 
 # Multi-Server Support
 
-MCP-Use supports working with multiple MCP servers simultaneously, allowing you to combine tools from different servers in a single agent. This is useful for complex tasks that require multiple capabilities, such as web browsing combined with file operations or 3D modeling.
+MCP-Use allows configuring and connecting to multiple MCP servers simultaneously using the `MCPClient`. This enables complex workflows that require tools from different servers, such as web browsing combined with file operations or 3D modeling.
 
 ## Configuration
 
@@ -415,7 +416,28 @@ You can configure multiple servers in your configuration file:
 
 ## Usage
 
-The `MCPClient` class provides several methods for managing multiple servers:
+The `MCPClient` class provides methods for managing connections to multiple servers. When creating an `MCPAgent`, you can provide an `MCPClient` configured with multiple servers.
+
+By default, the agent will have access to tools from all configured servers. If you need to target a specific server for a particular task, you can specify the `server_name` when calling the `agent.run()` method.
+
+```python
+# Example: Manually selecting a server for a specific task
+result = await agent.run(
+    "Search for Airbnb listings in Barcelona",
+    server_name="airbnb" # Explicitly use the airbnb server
+)
+
+result_google = await agent.run(
+    "Find restaurants near the first result using Google Search",
+    server_name="playwright" # Explicitly use the playwright server
+)
+```
+
+## Dynamic Server Selection (Server Manager)
+
+For enhanced efficiency and to reduce potential agent confusion when dealing with many tools from different servers, you can enable the Server Manager by setting `use_server_manager=True` during `MCPAgent` initialization.
+
+When enabled, the agent intelligently selects the correct MCP server based on the tool chosen by the LLM for a specific step. This minimizes unnecessary connections and ensures the agent uses the appropriate tools for the task.
 
 ```python
 import asyncio
@@ -429,7 +451,8 @@ async def main():
     # Create agent with the client
     agent = MCPAgent(
         llm=ChatAnthropic(model="claude-3-5-sonnet-20240620"),
-        client=client
+        client=client,
+        use_server_manager=True  # Enable the Server Manager
     )
 
     try:
@@ -480,6 +503,63 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+
+# Debugging
+
+MCP-Use provides a built-in debug mode that increases log verbosity and helps diagnose issues in your agent implementation.
+
+## Enabling Debug Mode
+
+There are two primary ways to enable debug mode:
+
+### 1. Environment Variable (Recommended for One-off Runs)
+
+Run your script with the `DEBUG` environment variable set to the desired level:
+
+```bash
+# Level 1: Show INFO level messages
+DEBUG=1 python3.11 examples/browser_use.py
+
+# Level 2: Show DEBUG level messages (full verbose output)
+DEBUG=2 python3.11 examples/browser_use.py
+```
+
+This sets the debug level only for the duration of that specific Python process.
+
+Alternatively you can set the following environment variable to the desired logging level:
+
+```bash
+export MCP_USE_DEBUG=1 # or 2
+```
+
+### 2. Setting the Debug Flag Programmatically
+
+You can set the global debug flag directly in your code:
+
+```python
+import mcp_use
+
+mcp_use.set_debug(1)  # INFO level
+# or
+mcp_use.set_debug(2)  # DEBUG level (full verbose output)
+```
+
+### 3. Agent-Specific Verbosity
+
+If you only want to see debug information from the agent without enabling full debug logging, you can set the `verbose` parameter when creating an MCPAgent:
+
+```python
+# Create agent with increased verbosity
+agent = MCPAgent(
+    llm=your_llm,
+    client=your_client,
+    verbose=True  # Only shows debug messages from the agent
+)
+```
+
+This is useful when you only need to see the agent's steps and decision-making process without all the low-level debug information from other components.
+
+
 # Roadmap
 
 <ul>
@@ -488,6 +568,10 @@ if __name__ == "__main__":
 <li>[ ] ... </li>
 </ul>
 
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=pietrozullo/mcp-use&type=Date)](https://www.star-history.com/#pietrozullo/mcp-use&Date)
+
 # Contributing
 
 We love contributions! Feel free to open issues for bugs or feature requests.

{mcp_use-1.1.4 → mcp_use-1.2.5}/README.md

@@ -2,9 +2,9 @@
   <img alt="" src="./static/image.jpg"  width="full">
 </picture>
 
-<h1 align="center">Open Source MCP CLient Library </h1>
+<h1 align="center">Unified MCP Client Library </h1>
 
-[![](https://img.shields.io/pypi/dd/mcp_use.svg)](https://pypi.org/project/mcp_use/)
+[![](https://img.shields.io/pypi/dw/mcp_use.svg)](https://pypi.org/project/mcp_use/)
 [![PyPI Downloads](https://img.shields.io/pypi/dm/mcp_use.svg)](https://pypi.org/project/mcp_use/)
 [![PyPI Version](https://img.shields.io/pypi/v/mcp_use.svg)](https://pypi.org/project/mcp_use/)
 [![Python Versions](https://img.shields.io/pypi/pyversions/mcp_use.svg)](https://pypi.org/project/mcp_use/)
@@ -12,8 +12,9 @@
 [![License](https://img.shields.io/github/license/pietrozullo/mcp-use)](https://github.com/pietrozullo/mcp-use/blob/main/LICENSE)
 [![Code style: Ruff](https://img.shields.io/badge/code%20style-ruff-000000.svg)](https://github.com/astral-sh/ruff)
 [![GitHub stars](https://img.shields.io/github/stars/pietrozullo/mcp-use?style=social)](https://github.com/pietrozullo/mcp-use/stargazers)
+[![Twitter Follow](https://img.shields.io/twitter/follow/Pietro?style=social)](https://x.com/pietrozullo)
 
-🌐 MCP-Use is the open source way to connect any LLM to MCP tools and build custom agents that have tool access, without using closed source or application clients.
+🌐 MCP-Use is the open source way to connect **any LLM to any MCP server** and build custom agents that have tool access, without using closed source or application clients.
 
 💡 Let developers easily connect any LLM to tools like web browsing, file operations, and more.
 
@@ -26,6 +27,7 @@
 | 🔄 **Ease of use** | Create your first MCP capable agent you need only 6 lines of code |
 | 🤖 **LLM Flexibility** | Works with any langchain supported LLM that supports tool calling (OpenAI, Anthropic, Groq, LLama etc.) |
 | 🌐 **HTTP Support** | Direct connection to MCP servers running on specific HTTP ports |
+| ⚙️ **Dynamic Server Selection** | Agents can dynamically choose the most appropriate MCP server for a given task from the available pool |
 | 🧩 **Multi-Server Support** | Use multiple MCP servers simultaneously in a single agent |
 | 🛡️ **Tool Restrictions** | Restrict potentially dangerous tools like file system or network access |
 
@@ -140,7 +142,6 @@ Example configuration file (`browser_mcp.json`):
 
 For other settings, models, and more, check out the documentation.
 
-# Features
 
 # Example Use Cases
 
@@ -350,7 +351,7 @@ This example demonstrates how to connect to an MCP server running on a specific
 
 # Multi-Server Support
 
-MCP-Use supports working with multiple MCP servers simultaneously, allowing you to combine tools from different servers in a single agent. This is useful for complex tasks that require multiple capabilities, such as web browsing combined with file operations or 3D modeling.
+MCP-Use allows configuring and connecting to multiple MCP servers simultaneously using the `MCPClient`. This enables complex workflows that require tools from different servers, such as web browsing combined with file operations or 3D modeling.
 
 ## Configuration
 
@@ -376,7 +377,28 @@ You can configure multiple servers in your configuration file:
 
 ## Usage
 
-The `MCPClient` class provides several methods for managing multiple servers:
+The `MCPClient` class provides methods for managing connections to multiple servers. When creating an `MCPAgent`, you can provide an `MCPClient` configured with multiple servers.
+
+By default, the agent will have access to tools from all configured servers. If you need to target a specific server for a particular task, you can specify the `server_name` when calling the `agent.run()` method.
+
+```python
+# Example: Manually selecting a server for a specific task
+result = await agent.run(
+    "Search for Airbnb listings in Barcelona",
+    server_name="airbnb" # Explicitly use the airbnb server
+)
+
+result_google = await agent.run(
+    "Find restaurants near the first result using Google Search",
+    server_name="playwright" # Explicitly use the playwright server
+)
+```
+
+## Dynamic Server Selection (Server Manager)
+
+For enhanced efficiency and to reduce potential agent confusion when dealing with many tools from different servers, you can enable the Server Manager by setting `use_server_manager=True` during `MCPAgent` initialization.
+
+When enabled, the agent intelligently selects the correct MCP server based on the tool chosen by the LLM for a specific step. This minimizes unnecessary connections and ensures the agent uses the appropriate tools for the task.
 
 ```python
 import asyncio
@@ -390,7 +412,8 @@ async def main():
     # Create agent with the client
     agent = MCPAgent(
         llm=ChatAnthropic(model="claude-3-5-sonnet-20240620"),
-        client=client
+        client=client,
+        use_server_manager=True  # Enable the Server Manager
     )
 
     try:
@@ -441,6 +464,63 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+
+# Debugging
+
+MCP-Use provides a built-in debug mode that increases log verbosity and helps diagnose issues in your agent implementation.
+
+## Enabling Debug Mode
+
+There are two primary ways to enable debug mode:
+
+### 1. Environment Variable (Recommended for One-off Runs)
+
+Run your script with the `DEBUG` environment variable set to the desired level:
+
+```bash
+# Level 1: Show INFO level messages
+DEBUG=1 python3.11 examples/browser_use.py
+
+# Level 2: Show DEBUG level messages (full verbose output)
+DEBUG=2 python3.11 examples/browser_use.py
+```
+
+This sets the debug level only for the duration of that specific Python process.
+
+Alternatively you can set the following environment variable to the desired logging level:
+
+```bash
+export MCP_USE_DEBUG=1 # or 2
+```
+
+### 2. Setting the Debug Flag Programmatically
+
+You can set the global debug flag directly in your code:
+
+```python
+import mcp_use
+
+mcp_use.set_debug(1)  # INFO level
+# or
+mcp_use.set_debug(2)  # DEBUG level (full verbose output)
+```
+
+### 3. Agent-Specific Verbosity
+
+If you only want to see debug information from the agent without enabling full debug logging, you can set the `verbose` parameter when creating an MCPAgent:
+
+```python
+# Create agent with increased verbosity
+agent = MCPAgent(
+    llm=your_llm,
+    client=your_client,
+    verbose=True  # Only shows debug messages from the agent
+)
+```
+
+This is useful when you only need to see the agent's steps and decision-making process without all the low-level debug information from other components.
+
+
 # Roadmap
 
 <ul>
@@ -449,6 +529,10 @@ if __name__ == "__main__":
 <li>[ ] ... </li>
 </ul>
 
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=pietrozullo/mcp-use&type=Date)](https://www.star-history.com/#pietrozullo/mcp-use&Date)
+
 # Contributing
 
 We love contributions! Feel free to open issues for bugs or feature requests.

{mcp_use-1.1.4 → mcp_use-1.2.5}/docs/api-reference/introduction.mdx

@@ -128,7 +128,8 @@ agent = MCPAgent(
     system_prompt=None,
     system_prompt_template=None,
     additional_instructions=None,
-    disallowed_tools=None
+    disallowed_tools=None,
+    use_server_manager=False
 )
 ```
 
@@ -146,6 +147,7 @@ agent = MCPAgent(
 | `additional_instructions` | str                 | No       | None    | Additional instructions for the agent                        |
 | `session_options`         | dict                | No       | {}      | Additional options for session creation                      |
 | `output_parser`           | OutputParser        | No       | None    | Custom output parser for LLM responses                       |
+| `use_server_manager`      | bool                | No       | False   | If `True`, enables automatic selection of the appropriate server based on the chosen tool when multiple servers are configured via `MCPClient`. |
 | `disallowed_tools`        | list[str]           | No       | None    | List of tool names that should not be available to the agent |
 
 **When to use different parameters**:
@@ -178,6 +180,9 @@ agent = MCPAgent(
 - **session_options**:
   - Customize timeout for long-running server operations
   - Set retry parameters for unstable connections
+- **use_server_manager**:
+  - Set to `True` when using an `MCPClient` configured with multiple servers to enable efficient, automatic server selection per tool call. This can reduce agent confusion and minimize unnecessary server connections.
+  - Keep as `False` (default) if using a single server or if you prefer to manually specify the target server using the `server_name` parameter in `agent.run()` or rely on the agent to handle tool availability across all connected servers.
 - **disallowed_tools**:
   - Use to restrict which tools the agent can access
   - Helpful for security or to limit agent capabilities

{mcp_use-1.1.4 → mcp_use-1.2.5}/docs/docs.json

@@ -19,7 +19,7 @@
           },
           {
             "group": "Essentials",
-            "pages": ["essentials/configuration", "essentials/llm-integration"]
+            "pages": ["essentials/configuration", "essentials/llm-integration", "essentials/debugging", "essentials/connection-types"]
           },
           {
             "group": "API Reference",

{mcp_use-1.1.4 → mcp_use-1.2.5}/docs/essentials/configuration.mdx

@@ -66,7 +66,7 @@ The configuration is defined in a JSON file with the following structure:
 }
 ```
 
-MCP servers can use different connection types (STDIO, HTTP, or WebSocket). For details on these connection types and how to configure them, see the [Connection Types](./connection-types) guide.
+MCP servers can use different connection types (STDIO, HTTP). For details on these connection types and how to configure them, see the [Connection Types](./connection-types) guide.
 
 ### Configuration Options
 

{mcp_use-1.1.4 → mcp_use-1.2.5}/docs/essentials/connection-types.mdx

@@ -58,32 +58,6 @@ HTTP connections communicate with MCP servers over standard HTTP/HTTPS protocols
 }
 ```
 
-## WebSocket (WS) Connections
-
-WebSocket connections provide a persistent, bidirectional communication channel between the client and server.
-
-### Characteristics:
-
-- **Real-time Communication**: Low-latency bidirectional data flow
-- **Persistent Connection**: Maintains connection state
-- **Efficiency**: Lower overhead for multiple interactions
-- **Event-Driven**: Well-suited for streaming and event-based operations
-
-### Configuration Example:
-
-```json
-{
-  "mcpServers": {
-    "ws_server": {
-      "url": "ws://localhost:3001",
-      "headers": {
-        "Authorization": "Bearer ${AUTH_TOKEN}"
-      }
-    }
-  }
-}
-```
-
 ## Choosing the Right Connection Type
 
 The choice of connection type depends on your specific use case:
@@ -92,8 +66,6 @@ The choice of connection type depends on your specific use case:
 
 2. **HTTP**: Ideal for stateless operations, simple integrations, and when working with existing HTTP infrastructure
 
-3. **WebSocket**: Preferred for real-time applications, streaming data, and scenarios requiring persistent connections
-
 When configuring your mcp_use environment, you can specify the connection type in your configuration file as shown in the examples above.
 
 ## Using Connection Types
@@ -111,7 +83,6 @@ For example:
 
 - If your configuration includes `command` and `args`, a STDIO connection will be used
 - If your configuration has a `url` starting with `http://` or `https://`, an HTTP connection will be used
-- If your configuration has a `url` starting with `ws://` or `wss://`, a WebSocket connection will be used
 
 This automatic inference simplifies the configuration process and ensures the appropriate connection type is used without requiring explicit specification.
 

mcp_use-1.2.5/docs/essentials/debugging.mdx

@@ -0,0 +1,103 @@
+---
+title: 'Debugging'
+description: 'Learn how to debug and log in mcp-use'
+---
+
+# Debugging MCP-Use
+
+MCP-Use provides built-in debugging functionality that increases log verbosity and helps diagnose issues in your agent implementation.
+
+## Enabling Debug Mode
+
+There are two primary ways to enable debug mode:
+
+### 1. Environment Variable (Recommended for One-off Runs)
+
+Run your script with the `DEBUG` environment variable set to the desired level:
+
+```bash
+# Level 1: Show INFO level messages
+DEBUG=1 python3.11 examples/browser_use.py
+
+# Level 2: Show DEBUG level messages (full verbose output)
+DEBUG=2 python3.11 examples/browser_use.py
+```
+
+This sets the debug level only for the duration of that specific Python process. This is particularly useful for quickly troubleshooting issues without modifying your code.
+Alternatively you can set the environment variable MCP_USE_DEBUG as such:
+```bash
+export MCP_USE_DEBUG=1 # or 2
+```
+
+### 2. Setting the Debug Flag Programmatically
+
+You can set the global debug flag directly in your code, which is useful for debugging specific parts of your application or conditionally enabling debug mode based on your application state:
+
+```python
+import mcp_use
+
+mcp_use.set_debug(1)  # INFO level
+# or
+mcp_use.set_debug(2)  # DEBUG level (full verbose output)
+# or
+mcp_use.set_debug(0)  # Turn off debug (WARNING level)
+```
+
+## Debug Levels
+
+MCP-Use supports different levels of debugging:
+
+| Level | Environment Variable | Program Setting | Description |
+|-------|---------------------|-----------------|-------------|
+| 0     | (not set)           | `set_debug(0)`  | Normal operation, only WARNING and above messages are shown |
+| 1     | `DEBUG=1`           | `set_debug(1)`  | INFO level messages are shown - useful for basic operational information. Shows tool calls.|
+| 2     | `DEBUG=2`           | `set_debug(2)`  | Full DEBUG level - all detailed debugging information is shown |
+
+## Agent-Specific Verbosity
+
+If you only want to increase verbosity for the agent component without enabling full debug mode for the entire package, you can use the `verbose` parameter when creating an MCPAgent:
+
+```python
+from mcp_use import MCPAgent
+
+# Create agent with increased verbosity
+agent = MCPAgent(
+    llm=your_llm,
+    client=your_client,
+    verbose=True  # Only shows debug messages from the agent
+)
+```
+
+This option is useful when you want to see the agent's steps and decision-making process without all the low-level debug information from other components.
+
+## Debug Information
+
+When debug mode is enabled, you'll see more detailed information about:
+
+- Server initialization and connection details
+- Tool registration and resolution
+- Agent steps and decision-making
+- Request and response formats
+- Communication with MCP servers
+- Error details and stack traces
+
+This can be extremely helpful when diagnosing issues with custom MCP servers or understanding why an agent might be behaving unexpectedly.
+
+## Langsmith
+
+Langchain offers a very nice tool to debug agent behaviour which integrates seamlessly with mcp-use. You can visit https://smith.langchain.com/ and login, they will give you a set of variables to copy in an .env file
+you will be then able to visualize the agent behaviour on their platform.
+
+## Troubleshooting Common Issues
+
+### Server Connection Problems
+
+If you're having issues connecting to MCP servers, enabling debug mode will show detailed information about the connection attempts, server initialization, and any errors encountered.
+
+### Agent Not Using Expected Tools
+
+When debug mode is enabled, you'll see each tool registration and the exact prompts being sent to the LLM, which can help diagnose why certain tools might not be used as expected.
+
+### Performance Issues
+
+Debug logs can help identify potential bottlenecks in your implementation by showing timing information for various operations.

{mcp_use-1.1.4 → mcp_use-1.2.5}/docs/introduction.mdx

@@ -28,6 +28,9 @@ mcp_use is an open source library that enables developers to connect any Languag
   <Card title="HTTP Connection" icon="network" href="/quickstart">
     Connect to MCP servers running on specific HTTP ports for web-based integrations
   </Card>
+  <Card title="Dynamic Server Selection" icon="shuffle" href="/quickstart">
+    Agents can dynamically choose the most appropriate MCP server for the task.
+  </Card>
 </CardGroup>
 
 ## Getting Started

{mcp_use-1.1.4 → mcp_use-1.2.5}/docs/quickstart.mdx

@@ -121,6 +121,65 @@ Example configuration file (`browser_mcp.json`):
 }
 ```
 
+## Using 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).
+
+**Configuration:**
+
+Define multiple servers in your configuration file (`multi_server_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "airbnb": {
+      "command": "npx",
+      "args": ["-y", "@openbnb/mcp-server-airbnb", "--ignore-robots-txt"]
+    },
+    "playwright": {
+      "command": "npx",
+      "args": ["@playwright/mcp@latest"],
+      "env": {
+        "DISPLAY": ":1"
+      }
+    }
+  }
+}
+```
+
+**Usage:**
+
+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"
+)
+```
+
+## Enabling Dynamic Server Selection (Server Manager)
+
+To improve efficiency and potentially reduce agent confusion when many tools are available, you can enable the Server Manager. Set `use_server_manager=True` when creating the `MCPAgent`.
+
+When enabled, the agent will automatically select the appropriate server based on the tool chosen by the LLM for each step. This avoids connecting to unnecessary servers.
+
+```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, use_server_manager=True) # Enable server manager
+
+# The agent can now use tools from both airbnb and playwright servers
+result = await agent.run(
+    "Search for a place in Barcelona on Airbnb, then Google nearby restaurants."
+)
+```
+
 ## Restricting Tool Access
 
 You can control which tools are available to the agent:
@@ -177,7 +236,6 @@ if __name__ == "__main__":
 
 mcp_use supports any MCP server, allowing you to connect to a wide range of server implementations. For a comprehensive list of available servers, check out the [awesome-mcp-servers](https://github.com/punkpeye/awesome-mcp-servers) repository.
 
-
 Each server requires its own configuration. Check the [Configuration Guide](/essentials/configuration) for details.
 
 ## HTTP Connection

{mcp_use-1.1.4 → mcp_use-1.2.5}/examples/browser_use.py

@@ -35,7 +35,10 @@ async def main():
 
     # Run the query
     result = await agent.run(
-        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
+        """
+        Navigate to https://github.com/mcp-use/mcp-use, give a star to the project and write
+        a summary of the project.
+        """,
         max_steps=30,
     )
     print(f"\nResult: {result}")

{mcp_use-1.1.4 → mcp_use-1.2.5}/examples/filesystem_use.py

@@ -22,7 +22,7 @@ config = {
             "args": [
                 "-y",
                 "@modelcontextprotocol/server-filesystem",
-                "/home/pietro/projects/mcp-use/",
+                "THE_PATH_TO_YOUR_DIRECTORY",
             ],
         }
     }

{mcp_use-1.1.4 → mcp_use-1.2.5}/examples/multi_server_example.py

@@ -37,7 +37,7 @@ async def run_multi_server_example():
                 "args": [
                     "-y",
                     "@modelcontextprotocol/server-filesystem",
-                    "/home/pietro/projects/mcp-use/",
+                    "YOUR_DIRECTORY_HERE",
                 ],
             },
         }

{mcp_use-1.1.4 → mcp_use-1.2.5}/mcp_use/__init__.py

@@ -11,7 +11,7 @@ from .agents.mcpagent import MCPAgent
 from .client import MCPClient
 from .config import load_config_file
 from .connectors import BaseConnector, HttpConnector, StdioConnector, WebSocketConnector
-from .logging import logger
+from .logging import MCP_USE_DEBUG, Logger, logger
 from .session import MCPSession
 
 __version__ = version("mcp-use")
@@ -27,4 +27,17 @@ __all__ = [
     "create_session_from_config",
     "load_config_file",
     "logger",
+    "MCP_USE_DEBUG",
+    "Logger",
+    "set_debug",
 ]
+
+
+# Helper function to set debug mode
+def set_debug(debug=2):
+    """Set the debug mode for mcp_use.
+
+    Args:
+        debug: Whether to enable debug mode (default: True)
+    """
+    Logger.set_debug(debug)