mcp-use 1.0.2__tar.gz → 1.1.4__tar.gz

mcp_use-1.1.4/.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,38 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**To Reproduce**
+Steps to reproduce the behavior:
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. iOS]
+ - Browser [e.g. chrome, safari]
+ - Version [e.g. 22]
+
+**Smartphone (please complete the following information):**
+ - Device: [e.g. iPhone6]
+ - OS: [e.g. iOS8.1]
+ - Browser [e.g. stock browser, safari]
+ - Version [e.g. 22]
+
+**Additional context**
+Add any other context about the problem here.

{mcp_use-1.0.2 → mcp_use-1.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-use
-Version: 1.0.2
+Version: 1.1.4
 Summary: MCP Library for LLMs
 Author-email: Pietro Zullo <pietro.zullo@gmail.com>
 License: MIT
@@ -56,6 +56,19 @@ Description-Content-Type: text/markdown
 
 💡 Let developers easily connect any LLM to tools like web browsing, file operations, and more.
 
+# Features
+
+## ✨ Key Features
+
+| Feature | Description |
+|---------|-------------|
+| 🔄 **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 |
+| 🧩 **Multi-Server Support** | Use multiple MCP servers simultaneously in a single agent |
+| 🛡️ **Tool Restrictions** | Restrict potentially dangerous tools like file system or network access |
+
+
 # Quick start
 
 With pip:
@@ -72,7 +85,30 @@ cd mcp-use
 pip install -e .
 ```
 
-Spin up your agent:
+### Installing LangChain Providers
+
+mcp_use works with various LLM providers through LangChain. You'll need to install the appropriate LangChain provider package for your chosen LLM. For example:
+
+```bash
+# For OpenAI
+pip install langchain-openai
+
+# For Anthropic
+pip install langchain-anthropic
+
+# For other providers, check the [LangChain chat models documentation](https://python.langchain.com/docs/integrations/chat/)
+```
+
+and add your API keys for the provider you want to use to your `.env` file.
+
+```bash
+OPENAI_API_KEY=
+ANTHROPIC_API_KEY=
+```
+
+> **Important**: Only models with tool calling capabilities can be used with mcp_use. Make sure your chosen model supports function calling or tool use.
+
+### Spin up your agent:
 
 ```python
 import asyncio
@@ -85,8 +121,21 @@ async def main():
     # Load environment variables
     load_dotenv()
 
-    # Create MCPClient from config file
-    client = MCPClient.from_config_file("browser_mcp.json")
+    # Create configuration dictionary
+    config = {
+      "mcpServers": {
+        "playwright": {
+          "command": "npx",
+          "args": ["@playwright/mcp@latest"],
+          "env": {
+            "DISPLAY": ":1"
+          }
+        }
+      }
+    }
+
+    # Create MCPClient from configuration dictionary
+    client = MCPClient.from_dict(config)
 
     # Create LLM
     llm = ChatOpenAI(model="gpt-4o")
@@ -96,7 +145,7 @@ async def main():
 
     # Run the query
     result = await agent.run(
-        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
+        "Find the best restaurant in San Francisco",
     )
     print(f"\nResult: {result}")
 
@@ -104,6 +153,14 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+You can also add the servers configuration from a config file like this:
+
+```python
+client = MCPClient.from_config_file(
+        os.path.join("browser_mcp.json")
+    )
+```
+
 Example configuration file (`browser_mcp.json`):
 
 ```json
@@ -120,15 +177,10 @@ Example configuration file (`browser_mcp.json`):
 }
 ```
 
-Add your API keys for the provider you want to use to your `.env` file.
-
-```bash
-OPENAI_API_KEY=
-ANTHROPIC_API_KEY=
-```
-
 For other settings, models, and more, check out the documentation.
 
+# Features
+
 # Example Use Cases
 
 ## Web Browsing with Playwright
@@ -286,6 +338,55 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+## HTTP Connection Example
+
+MCP-Use now supports HTTP connections, allowing you to connect to MCP servers running on specific HTTP ports. This feature is particularly useful for integrating with web-based MCP servers.
+
+Here's an example of how to use the HTTP connection feature:
+
+```python
+import asyncio
+import os
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from mcp_use import MCPAgent, MCPClient
+
+async def main():
+    """Run the example using a configuration file."""
+    # Load environment variables
+    load_dotenv()
+
+    config = {
+        "mcpServers": {
+            "http": {
+                "url": "http://localhost:8931/sse"
+            }
+        }
+    }
+
+    # Create MCPClient from config file
+    client = MCPClient.from_dict(config)
+
+    # Create LLM
+    llm = ChatOpenAI(model="gpt-4o")
+
+    # Create agent with the client
+    agent = MCPAgent(llm=llm, client=client, max_steps=30)
+
+    # Run the query
+    result = await agent.run(
+        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
+        max_steps=30,
+    )
+    print(f"\nResult: {result}")
+
+if __name__ == "__main__":
+    # Run the appropriate example
+    asyncio.run(main())
+```
+
+This example demonstrates how to connect to an MCP server running on a specific HTTP port. Make sure to start your MCP server before running this example.
+
 # 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.
@@ -346,25 +447,58 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-## Roadmap
+# Tool Access Control
+
+MCP-Use allows you to restrict which tools are available to the agent, providing better security and control over agent capabilities:
+
+```python
+import asyncio
+from mcp_use import MCPAgent, MCPClient
+from langchain_openai import ChatOpenAI
+
+async def main():
+    # Create client
+    client = MCPClient.from_config_file("config.json")
+
+    # Create agent with restricted tools
+    agent = MCPAgent(
+        llm=ChatOpenAI(model="gpt-4"),
+        client=client,
+        disallowed_tools=["file_system", "network"]  # Restrict potentially dangerous tools
+    )
+
+    # Run a query with restricted tool access
+    result = await agent.run(
+        "Find the best restaurant in San Francisco"
+    )
+    print(result)
+
+    # Clean up
+    await client.close_all_sessions()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+# Roadmap
 
 <ul>
 <li>[x] Multiple Servers at once </li>
-<li>[ ] Test remote connectors (http, ws)</li>
+<li>[x] Test remote connectors (http, ws)</li>
 <li>[ ] ... </li>
 </ul>
 
-## Contributing
+# Contributing
 
 We love contributions! Feel free to open issues for bugs or feature requests.
 
-## Requirements
+# Requirements
 
 - Python 3.11+
 - MCP implementation (like Playwright MCP)
 - LangChain and appropriate model libraries (OpenAI, Anthropic, etc.)
 
-## Citation
+# Citation
 
 If you use MCP-Use in your research or project, please cite:
 
@@ -378,6 +512,6 @@ If you use MCP-Use in your research or project, please cite:
 }
 ```
 
-## License
+# License
 
 MIT

{mcp_use-1.0.2 → mcp_use-1.1.4}/README.md

@@ -17,6 +17,19 @@
 
 💡 Let developers easily connect any LLM to tools like web browsing, file operations, and more.
 
+# Features
+
+## ✨ Key Features
+
+| Feature | Description |
+|---------|-------------|
+| 🔄 **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 |
+| 🧩 **Multi-Server Support** | Use multiple MCP servers simultaneously in a single agent |
+| 🛡️ **Tool Restrictions** | Restrict potentially dangerous tools like file system or network access |
+
+
 # Quick start
 
 With pip:
@@ -33,7 +46,30 @@ cd mcp-use
 pip install -e .
 ```
 
-Spin up your agent:
+### Installing LangChain Providers
+
+mcp_use works with various LLM providers through LangChain. You'll need to install the appropriate LangChain provider package for your chosen LLM. For example:
+
+```bash
+# For OpenAI
+pip install langchain-openai
+
+# For Anthropic
+pip install langchain-anthropic
+
+# For other providers, check the [LangChain chat models documentation](https://python.langchain.com/docs/integrations/chat/)
+```
+
+and add your API keys for the provider you want to use to your `.env` file.
+
+```bash
+OPENAI_API_KEY=
+ANTHROPIC_API_KEY=
+```
+
+> **Important**: Only models with tool calling capabilities can be used with mcp_use. Make sure your chosen model supports function calling or tool use.
+
+### Spin up your agent:
 
 ```python
 import asyncio
@@ -46,8 +82,21 @@ async def main():
     # Load environment variables
     load_dotenv()
 
-    # Create MCPClient from config file
-    client = MCPClient.from_config_file("browser_mcp.json")
+    # Create configuration dictionary
+    config = {
+      "mcpServers": {
+        "playwright": {
+          "command": "npx",
+          "args": ["@playwright/mcp@latest"],
+          "env": {
+            "DISPLAY": ":1"
+          }
+        }
+      }
+    }
+
+    # Create MCPClient from configuration dictionary
+    client = MCPClient.from_dict(config)
 
     # Create LLM
     llm = ChatOpenAI(model="gpt-4o")
@@ -57,7 +106,7 @@ async def main():
 
     # Run the query
     result = await agent.run(
-        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
+        "Find the best restaurant in San Francisco",
     )
     print(f"\nResult: {result}")
 
@@ -65,6 +114,14 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+You can also add the servers configuration from a config file like this:
+
+```python
+client = MCPClient.from_config_file(
+        os.path.join("browser_mcp.json")
+    )
+```
+
 Example configuration file (`browser_mcp.json`):
 
 ```json
@@ -81,15 +138,10 @@ Example configuration file (`browser_mcp.json`):
 }
 ```
 
-Add your API keys for the provider you want to use to your `.env` file.
-
-```bash
-OPENAI_API_KEY=
-ANTHROPIC_API_KEY=
-```
-
 For other settings, models, and more, check out the documentation.
 
+# Features
+
 # Example Use Cases
 
 ## Web Browsing with Playwright
@@ -247,6 +299,55 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+## HTTP Connection Example
+
+MCP-Use now supports HTTP connections, allowing you to connect to MCP servers running on specific HTTP ports. This feature is particularly useful for integrating with web-based MCP servers.
+
+Here's an example of how to use the HTTP connection feature:
+
+```python
+import asyncio
+import os
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from mcp_use import MCPAgent, MCPClient
+
+async def main():
+    """Run the example using a configuration file."""
+    # Load environment variables
+    load_dotenv()
+
+    config = {
+        "mcpServers": {
+            "http": {
+                "url": "http://localhost:8931/sse"
+            }
+        }
+    }
+
+    # Create MCPClient from config file
+    client = MCPClient.from_dict(config)
+
+    # Create LLM
+    llm = ChatOpenAI(model="gpt-4o")
+
+    # Create agent with the client
+    agent = MCPAgent(llm=llm, client=client, max_steps=30)
+
+    # Run the query
+    result = await agent.run(
+        "Find the best restaurant in San Francisco USING GOOGLE SEARCH",
+        max_steps=30,
+    )
+    print(f"\nResult: {result}")
+
+if __name__ == "__main__":
+    # Run the appropriate example
+    asyncio.run(main())
+```
+
+This example demonstrates how to connect to an MCP server running on a specific HTTP port. Make sure to start your MCP server before running this example.
+
 # 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.
@@ -307,25 +408,58 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-## Roadmap
+# Tool Access Control
+
+MCP-Use allows you to restrict which tools are available to the agent, providing better security and control over agent capabilities:
+
+```python
+import asyncio
+from mcp_use import MCPAgent, MCPClient
+from langchain_openai import ChatOpenAI
+
+async def main():
+    # Create client
+    client = MCPClient.from_config_file("config.json")
+
+    # Create agent with restricted tools
+    agent = MCPAgent(
+        llm=ChatOpenAI(model="gpt-4"),
+        client=client,
+        disallowed_tools=["file_system", "network"]  # Restrict potentially dangerous tools
+    )
+
+    # Run a query with restricted tool access
+    result = await agent.run(
+        "Find the best restaurant in San Francisco"
+    )
+    print(result)
+
+    # Clean up
+    await client.close_all_sessions()
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+# Roadmap
 
 <ul>
 <li>[x] Multiple Servers at once </li>
-<li>[ ] Test remote connectors (http, ws)</li>
+<li>[x] Test remote connectors (http, ws)</li>
 <li>[ ] ... </li>
 </ul>
 
-## Contributing
+# Contributing
 
 We love contributions! Feel free to open issues for bugs or feature requests.
 
-## Requirements
+# Requirements
 
 - Python 3.11+
 - MCP implementation (like Playwright MCP)
 - LangChain and appropriate model libraries (OpenAI, Anthropic, etc.)
 
-## Citation
+# Citation
 
 If you use MCP-Use in your research or project, please cite:
 
@@ -339,6 +473,6 @@ If you use MCP-Use in your research or project, please cite:
 }
 ```
 
-## License
+# License
 
 MIT

{mcp_use-1.0.2 → mcp_use-1.1.4}/docs/api-reference/introduction.mdx

@@ -127,24 +127,26 @@ agent = MCPAgent(
     memory_enabled=True,
     system_prompt=None,
     system_prompt_template=None,
-    additional_instructions=None
+    additional_instructions=None,
+    disallowed_tools=None
 )
 ```
 
-| Parameter                 | Type                | Required | Default | Description                                |
-| ------------------------- | ------------------- | -------- | ------- | ------------------------------------------ |
-| `llm`                     | BaseLanguageModel   | Yes      | -       | Any LangChain-compatible language model    |
-| `client`                  | MCPClient           | No       | None    | The MCPClient instance                     |
-| `connectors`              | list[BaseConnector] | No       | None    | List of connectors if not using client     |
-| `server_name`             | str                 | No       | None    | Name of the server to use                  |
-| `max_steps`               | int                 | No       | 5       | Maximum number of steps the agent can take |
-| `auto_initialize`         | bool                | No       | False   | Whether to initialize automatically        |
-| `memory_enabled`          | bool                | No       | True    | Whether to enable memory                   |
-| `system_prompt`           | str                 | No       | None    | Custom system prompt                       |
-| `system_prompt_template`  | str                 | No       | None    | Custom system prompt template              |
-| `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     |
+| Parameter                 | Type                | Required | Default | Description                                                  |
+| ------------------------- | ------------------- | -------- | ------- | ------------------------------------------------------------ |
+| `llm`                     | BaseLanguageModel   | Yes      | -       | Any LangChain-compatible language model                      |
+| `client`                  | MCPClient           | No       | None    | The MCPClient instance                                       |
+| `connectors`              | list[BaseConnector] | No       | None    | List of connectors if not using client                       |
+| `server_name`             | str                 | No       | None    | Name of the server to use                                    |
+| `max_steps`               | int                 | No       | 5       | Maximum number of steps the agent can take                   |
+| `auto_initialize`         | bool                | No       | False   | Whether to initialize automatically                          |
+| `memory_enabled`          | bool                | No       | True    | Whether to enable memory                                     |
+| `system_prompt`           | str                 | No       | None    | Custom system prompt                                         |
+| `system_prompt_template`  | str                 | No       | None    | Custom system prompt template                                |
+| `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                       |
+| `disallowed_tools`        | list[str]           | No       | None    | List of tool names that should not be available to the agent |
 
 **When to use different parameters**:
 
@@ -176,6 +178,11 @@ agent = MCPAgent(
 - **session_options**:
   - Customize timeout for long-running server operations
   - Set retry parameters for unstable connections
+- **disallowed_tools**:
+  - Use to restrict which tools the agent can access
+  - Helpful for security or to limit agent capabilities
+  - Useful when certain tools might be dangerous or unnecessary for a specific task
+  - Can be updated after initialization using `set_disallowed_tools()`
 
 ### Core Methods
 
@@ -234,6 +241,39 @@ history = agent.get_history()
 - When implementing custom logging
 - To provide context for follow-up queries
 
+#### set_disallowed_tools
+
+Sets the list of tools that should not be available to the agent.
+
+```python
+agent.set_disallowed_tools(["tool1", "tool2"])
+```
+
+| Parameter          | Type      | Required | Description                                     |
+| ------------------ | --------- | -------- | ----------------------------------------------- |
+| `disallowed_tools` | list[str] | Yes      | List of tool names that should not be available |
+
+**When to use**:
+
+- To restrict access to specific tools for security reasons
+- To limit agent capabilities for specific tasks
+- To prevent the agent from using potentially dangerous tools
+- Note: Changes take effect on next initialization
+
+#### get_disallowed_tools
+
+Gets the list of tools that are not available to the agent.
+
+```python
+disallowed = agent.get_disallowed_tools()
+```
+
+**When to use**:
+
+- To check which tools are currently restricted
+- For debugging or auditing purposes
+- To verify tool restrictions before running the agent
+
 ## Configuration Details
 
 ### MCP Server Configuration Schema
@@ -383,3 +423,34 @@ This approach is useful when:
 - The MCP server returns structured data that needs special handling
 - You need to extract specific information from responses
 - You're integrating with custom or specialized MCP servers
+
+### Restricting Tool Access
+
+Control which tools are available to the agent:
+
+```python
+from mcp_use import MCPAgent, MCPClient
+from langchain_openai import ChatOpenAI
+
+# Create agent with restricted tools
+agent = MCPAgent(
+    llm=ChatOpenAI(model="gpt-4o"),
+    client=client,
+    disallowed_tools=["file_system", "network", "shell"]  # Restrict potentially dangerous tools
+)
+
+# Update restrictions after initialization
+agent.set_disallowed_tools(["file_system", "network", "shell", "database"])
+await agent.initialize()  # Reinitialize to apply changes
+
+# Check current restrictions
+restricted_tools = agent.get_disallowed_tools()
+print(f"Restricted tools: {restricted_tools}")
+```
+
+This approach is useful when:
+
+- You need to restrict access to sensitive operations
+- You want to limit the agent's capabilities for specific tasks
+- You're concerned about security implications of certain tools
+- You want to focus the agent on specific functionality