mcp-use 1.2.7__tar.gz → 1.2.9__tar.gz

{mcp_use-1.2.7 → mcp_use-1.2.9}/.github/workflows/tests.yml

@@ -22,7 +22,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install .[dev,anthropic,openai]
+          pip install .[dev,anthropic,openai,search]
       - name: Lint with ruff
         run: |
           ruff check .

{mcp_use-1.2.7 → mcp_use-1.2.9}/.pre-commit-config.yaml

@@ -4,10 +4,10 @@ repos:
     rev: v0.3.2
     hooks:
     -   id: ruff
-        args: [--fix, --exit-non-zero-on-fix, --config=pyproject.toml]
+        args: [--fix, --exit-non-zero-on-fix, --config=ruff.toml]
         types: [python]
     -   id: ruff-format
-        args: [--config=pyproject.toml]
+        args: [--config=ruff.toml]
         types: [python]
 
 -   repo: https://github.com/pre-commit/pre-commit-hooks

mcp_use-1.2.9/CONTRIBUTING.md

@@ -0,0 +1,146 @@
+# Contributing to MCP-Use
+
+Thank you for your interest in contributing to MCP-Use! This document provides guidelines and instructions for contributing to this project.
+
+## Table of Contents
+
+- [Getting Started](#getting-started)
+  - [Development Environment](#development-environment)
+  - [Installation from Source](#installation-from-source)
+- [Development Workflow](#development-workflow)
+  - [Branching Strategy](#branching-strategy)
+  - [Commit Messages](#commit-messages)
+  - [Code Style](#code-style)
+  - [Pre-commit Hooks](#pre-commit-hooks)
+- [Testing](#testing)
+  - [Running Tests](#running-tests)
+  - [Adding Tests](#adding-tests)
+- [Pull Requests](#pull-requests)
+  - [Creating a Pull Request](#creating-a-pull-request)
+  - [Pull Request Template](#pull-request-template)
+- [Documentation](#documentation)
+- [Release Process](#release-process)
+- [Getting Help](#getting-help)
+
+## Getting Started
+
+### Development Environment
+
+MCP-Use requires:
+- Python 3.11 or later
+
+### Installation from Source
+
+1. Fork the repository on GitHub.
+2. Clone your fork locally:
+   ```bash
+   git clone https://github.com/YOUR_USERNAME/mcp-use.git
+   cd mcp-use
+   ```
+3. Install the package in development mode:
+   ```bash
+   pip install -e ".[dev,search]"
+   ```
+4. Set up pre-commit hooks:
+   ```bash
+   pip install pre-commit
+   pre-commit install
+   ```
+
+## Development Workflow
+
+### Branching Strategy
+
+- `main` branch contains the latest stable code
+- Create feature branches from `main` named according to the feature you're implementing: `feature/your-feature-name`
+- For bug fixes, use: `fix/bug-description`
+
+### Commit Messages
+
+For now no commit style is enforced, try to keep your commit messages informational.
+### Code Style
+
+We use [Ruff](https://github.com/astral-sh/ruff) for code formatting and linting. The configuration is in `ruff.toml`.
+
+Key style guidelines:
+- Line length: 100 characters
+- Use double quotes for strings
+- Follow PEP 8 naming conventions
+- Add type hints to function signatures
+
+### Pre-commit Hooks
+
+We use pre-commit hooks to ensure code quality before committing. The configuration is in `.pre-commit-config.yaml`.
+
+The hooks will:
+- Format code using Ruff
+- Run linting checks
+- Check for trailing whitespace and fix it
+- Ensure files end with a newline
+- Validate YAML files
+- Check for large files
+- Remove debug statements
+
+## Testing
+
+### Running Tests
+
+Run the test suite with pytest:
+
+```bash
+pytest
+```
+
+To run specific test categories:
+
+```bash
+pytest tests/
+```
+
+### Adding Tests
+
+- Add unit tests for new functionality in `tests/unit/`
+- For slow or network-dependent tests, mark them with `@pytest.mark.slow` or `@pytest.mark.integration`
+- Aim for high test coverage of new code
+
+## Pull Requests
+
+### Creating a Pull Request
+
+1. Ensure your code passes all tests and pre-commit hooks
+2. Push your changes to your fork
+3. Submit a pull request to the main repository
+4. Follow the pull request template
+
+## Documentation
+
+- Update docstrings for new or modified functions, classes, and methods
+- Use Google-style docstrings:
+  ```python
+  def function_name(param1: type, param2: type) -> return_type:
+      """Short description.
+
+      Longer description if needed.
+
+      Args:
+          param1: Description of param1
+          param2: Description of param2
+
+      Returns:
+          Description of return value
+
+      Raises:
+          ExceptionType: When and why this exception is raised
+      """
+  ```
+- Update README.md for user-facing changes
+
+## Getting Help
+
+If you need help with your contribution:
+
+- Open an issue for discussion
+- Reach out to the maintainers
+- Check existing code for examples
+
+Thank you for contributing to MCP-Use!

{mcp_use-1.2.7 → mcp_use-1.2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-use
-Version: 1.2.7
+Version: 1.2.9
 Summary: MCP Library for LLMs
 Author-email: Pietro Zullo <pietro.zullo@gmail.com>
 License: MIT
@@ -35,6 +35,8 @@ Requires-Dist: pytest>=7.4.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
 Provides-Extra: openai
 Requires-Dist: openai>=1.10.0; extra == 'openai'
+Provides-Extra: search
+Requires-Dist: fastembed>=0.0.1; extra == 'search'
 Description-Content-Type: text/markdown
 
 <picture>
@@ -48,6 +50,7 @@ Description-Content-Type: text/markdown
 [![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/)
 [![Documentation](https://img.shields.io/badge/docs-mcp--use.io-blue)](https://docs.mcp-use.io)
+[![Website](https://img.shields.io/badge/website-mcp--use.io-blue)](https://mcp-use.io)
 [![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)
@@ -63,13 +66,14 @@ Description-Content-Type: text/markdown
 
 | 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 |
-| ⚙️ **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 |
-| 🔧 **Custom Agents** | Build your own agents with any framework using the LangChain adapter or create new adapters |
+| 🔄 [**Ease of use**](#quick-start) | Create your first MCP capable agent you need only 6 lines of code |
+| 🤖 [**LLM Flexibility**](#installing-langchain-providers) | Works with any langchain supported LLM that supports tool calling (OpenAI, Anthropic, Groq, LLama etc.) |
+| 🌐 [**Code Builder**](https://mcp-use.io/builder) | Explore MCP capabilities and generate starter code with the interactive [code builder](https://mcp-use.io/builder). |
+| 🔗 [**HTTP Support**](#http-connection-example) | Direct connection to MCP servers running on specific HTTP ports |
+| ⚙️ [**Dynamic Server Selection**](#dynamic-server-selection-server-manager) | Agents can dynamically choose the most appropriate MCP server for a given task from the available pool |
+| 🧩 [**Multi-Server Support**](#multi-server-support) | Use multiple MCP servers simultaneously in a single agent |
+| 🛡️ [**Tool Restrictions**](#tool-access-control) | Restrict potentially dangerous tools like file system or network access |
+| 🔧 [**Custom Agents**](#build-a-custom-agent) | Build your own agents with any framework using the LangChain adapter or create new adapters |
 
 
 # Quick start
@@ -182,6 +186,43 @@ Example configuration file (`browser_mcp.json`):
 
 For other settings, models, and more, check out the documentation.
 
+## Streaming Agent Output
+
+MCP-Use supports asynchronous streaming of agent output using the `astream` method on `MCPAgent`. This allows you to receive incremental results, tool actions, and intermediate steps as they are generated by the agent, enabling real-time feedback and progress reporting.
+
+### How to use
+
+Call `agent.astream(query)` and iterate over the results asynchronously:
+
+```python
+async for chunk in agent.astream("Find the best restaurant in San Francisco"):
+    print(chunk["messages"], end="", flush=True)
+```
+
+Each chunk is a dictionary containing keys such as `actions`, `steps`, `messages`, and (on the last chunk) `output`. This enables you to build responsive UIs or log agent progress in real time.
+
+#### Example: Streaming in Practice
+
+```python
+import asyncio
+import os
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from mcp_use import MCPAgent, MCPClient
+
+async def main():
+    load_dotenv()
+    client = MCPClient.from_config_file("browser_mcp.json")
+    llm = ChatOpenAI(model="gpt-4o")
+    agent = MCPAgent(llm=llm, client=client, max_steps=30)
+    async for chunk in agent.astream("Look for job at nvidia for machine learning engineer."):
+        print(chunk["messages"], end="", flush=True)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+This streaming interface is ideal for applications that require real-time updates, such as chatbots, dashboards, or interactive notebooks.
 
 # Example Use Cases
 
@@ -342,7 +383,7 @@ if __name__ == "__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.
+MCP-Use 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:
 
@@ -610,7 +651,7 @@ This is useful when you only need to see the agent's steps and decision-making p
 
 # Contributing
 
-We love contributions! Feel free to open issues for bugs or feature requests.
+We love contributions! Feel free to open issues for bugs or feature requests. Look at [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 
 # Requirements
 

{mcp_use-1.2.7 → mcp_use-1.2.9}/README.md

@@ -9,6 +9,7 @@
 [![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/)
 [![Documentation](https://img.shields.io/badge/docs-mcp--use.io-blue)](https://docs.mcp-use.io)
+[![Website](https://img.shields.io/badge/website-mcp--use.io-blue)](https://mcp-use.io)
 [![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)
@@ -24,13 +25,14 @@
 
 | 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 |
-| ⚙️ **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 |
-| 🔧 **Custom Agents** | Build your own agents with any framework using the LangChain adapter or create new adapters |
+| 🔄 [**Ease of use**](#quick-start) | Create your first MCP capable agent you need only 6 lines of code |
+| 🤖 [**LLM Flexibility**](#installing-langchain-providers) | Works with any langchain supported LLM that supports tool calling (OpenAI, Anthropic, Groq, LLama etc.) |
+| 🌐 [**Code Builder**](https://mcp-use.io/builder) | Explore MCP capabilities and generate starter code with the interactive [code builder](https://mcp-use.io/builder). |
+| 🔗 [**HTTP Support**](#http-connection-example) | Direct connection to MCP servers running on specific HTTP ports |
+| ⚙️ [**Dynamic Server Selection**](#dynamic-server-selection-server-manager) | Agents can dynamically choose the most appropriate MCP server for a given task from the available pool |
+| 🧩 [**Multi-Server Support**](#multi-server-support) | Use multiple MCP servers simultaneously in a single agent |
+| 🛡️ [**Tool Restrictions**](#tool-access-control) | Restrict potentially dangerous tools like file system or network access |
+| 🔧 [**Custom Agents**](#build-a-custom-agent) | Build your own agents with any framework using the LangChain adapter or create new adapters |
 
 
 # Quick start
@@ -143,6 +145,43 @@ Example configuration file (`browser_mcp.json`):
 
 For other settings, models, and more, check out the documentation.
 
+## Streaming Agent Output
+
+MCP-Use supports asynchronous streaming of agent output using the `astream` method on `MCPAgent`. This allows you to receive incremental results, tool actions, and intermediate steps as they are generated by the agent, enabling real-time feedback and progress reporting.
+
+### How to use
+
+Call `agent.astream(query)` and iterate over the results asynchronously:
+
+```python
+async for chunk in agent.astream("Find the best restaurant in San Francisco"):
+    print(chunk["messages"], end="", flush=True)
+```
+
+Each chunk is a dictionary containing keys such as `actions`, `steps`, `messages`, and (on the last chunk) `output`. This enables you to build responsive UIs or log agent progress in real time.
+
+#### Example: Streaming in Practice
+
+```python
+import asyncio
+import os
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI
+from mcp_use import MCPAgent, MCPClient
+
+async def main():
+    load_dotenv()
+    client = MCPClient.from_config_file("browser_mcp.json")
+    llm = ChatOpenAI(model="gpt-4o")
+    agent = MCPAgent(llm=llm, client=client, max_steps=30)
+    async for chunk in agent.astream("Look for job at nvidia for machine learning engineer."):
+        print(chunk["messages"], end="", flush=True)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+This streaming interface is ideal for applications that require real-time updates, such as chatbots, dashboards, or interactive notebooks.
 
 # Example Use Cases
 
@@ -303,7 +342,7 @@ if __name__ == "__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.
+MCP-Use 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:
 
@@ -571,7 +610,7 @@ This is useful when you only need to see the agent's steps and decision-making p
 
 # Contributing
 
-We love contributions! Feel free to open issues for bugs or feature requests.
+We love contributions! Feel free to open issues for bugs or feature requests. Look at [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
 
 # Requirements
 

mcp_use-1.2.9/docs/api-reference/mcpagent.mdx

@@ -0,0 +1,21 @@
+## astream
+
+```python
+def astream(
+    query: str,
+    max_steps: int | None = None,
+    manage_connector: bool = True,
+    external_history: list[BaseMessage] | None = None,
+) -> AsyncIterator[dict]:
+```
+
+Asynchronous streaming interface for agent output. Yields incremental results, tool actions, and intermediate steps as they are generated by the agent.
+
+**Example:**
+
+```python
+async for chunk in agent.astream("hello"):
+    print(chunk["messages"], end="|", flush=True)
+```
+
+Each chunk is a dictionary containing keys such as `actions`, `steps`, `messages`, and (on the last chunk) `output`.

{mcp_use-1.2.7 → mcp_use-1.2.9}/docs/development.mdx

@@ -9,7 +9,7 @@ This guide will help you set up your development environment and contribute to m
 
 ## Prerequisites
 
-- Python 3.8 or higher
+- Python 3.11 or higher
 - Git
 - Node.js and npm (for MCP server dependencies)
 
@@ -112,24 +112,3 @@ mcp-use/
 ├── static/           # Static assets
 └── pyproject.toml    # Project configuration
 ```
-
-## Adding New MCP Servers
-
-To add support for a new MCP server:
-
-1. Create a new configuration template in the examples directory
-2. Add necessary server-specific code in the `mcp_use` package
-3. Update documentation with new server information
-4. Add tests for the new server functionality
-
-## Release Process
-
-1. Update version in `pyproject.toml`
-2. Update CHANGELOG.md
-3. Create a new release tag
-4. Build and publish to PyPI:
-
-```bash
-python -m build
-python -m twine upload dist/*
-```

{mcp_use-1.2.7 → mcp_use-1.2.9}/docs/docs.json

@@ -27,6 +27,7 @@
               "essentials/llm-integration",
               "essentials/debugging",
               "essentials/connection-types",
+              "essentials/server-manager",
               "building-custom-agents"
             ]
           },