# agentscope

> MCP Client

AgentScope is a framework designed to simplify the creation of LLM-powered multi-agent applications. It offers tools, documentation, and a drag-and-drop workstation for building and deploying agent-based systems. AgentScope is a

## Overview

- **Category:** AI
- **Language:** Python
- **Stars:** 28322
- **Forks:** 394
- **Owner:** modelscope
- **GitHub:** https://github.com/modelscope/agentscope
- **Homepage:** https://doc.agentscope.io/
- **Created:** 2024-01-12T03:41:59+00:00
- **Updated:** 2025-03-28T17:40:52+00:00
- **Source:** https://model-context-protocol.com/clients/llm-multi-agent-application-building-framework

## Setup

## Setup
AgentScope requires **Python 3.9** or higher.

***Note: This project is currently in active development, it's recommended to
install AgentScope from source.***

### From source

- Install AgentScope in editable mode:

```bash
# Pull the source code from GitHub
git clone https://github.com/modelscope/agentscope.git

# Install the package in editable mode
cd agentscope
pip install -e .
```

### Using pip

- Install AgentScope from pip:

```bash
pip install agentscope
```

### Extra Dependencies

To support different deployment scenarios, AgentScope provides several
optional dependencies. Full list of optional dependencies refers to
[tutorial](https://doc.agentscope.io/build_tutorial/quickstart.html)
Taking distribution mode as an example, you can install its dependencies
as follows:

#### On Windows

```bash
# From source
pip install -e .[distribute]
# From pypi
pip install agentscope[distribute]
```

#### On Mac & Linux

```bash
# From source
pip install -e .\\[distribute\\]
# From pypi
pip install agentscope\\[distribute\\]
```

We provide a developer version with additional pre-commit hooks to perform
checks compared to the official version:

```bash
# For windows
pip install -e .[dev]
# For mac
pip install -e .\\[dev\\]

# Install pre-commit hooks
pre-commit install
```

## Tools

## Available Tools

1.  Easy-to-Use: Designed for developers, with fruitful components, comprehensive documentation, and broad compatibility. 
2.  High Robustness: Supporting customized fault-tolerance controls and retry mechanisms to enhance application stability.
3.  Actor-Based Distribution: Building distributed multi-agent applications in a centralized programming manner for streamlined development.
4.  ModelWrapper: Supports both local model services and third-party model APIs.
5.  AgentScope Workstation: Provides a drag-and-drop programming platform and a copilot for beginners of AgentScope!
6.  AgentScope Studio: Provides an easy-to-use runtime user interface capable of displaying multimodal output on the front end, including text, images, audio and video.
7.  Web Search: Allows agents to search the web for information.
8.  Data Query: Enables agents to query and retrieve data from various sources.
9.  Retrieval: Supports information retrieval capabilities for agents.
10. Code Execution: Allows agents to execute code snippets.
11. File Operation: Enables agents to perform file-related operations.
12. Text Processing: Provides text processing functionalities for agents.
13. Multi Modality: Supports handling of multiple modalities of data.
14. Wikipedia Search and Retrieval: Allows agents to search and retrieve information from Wikipedia.
15. TripAdvisor Search: Enables agents to search for information on TripAdvisor.
16. Web Browser Control: Allows agents to control and interact with web browsers.

## Related Articles

- [agentscope: LLM Multi-Agent Application Framework and MCP Client](https://model-context-protocol.com/blog/agentscope-llm-multi-agent-application-framework-and-mcp-client-mcp-client-guide)