Agentis MCP: Build AI Agents, Seamless Integration

Agentis MCP: Build AI agents with MCP servers as tools using Python. Works seamlessly with any server and provider.

Visit Repository

✨ Developer Tools

4.4(73 reviews)

109 saves

51 comments

43% of users reported increased productivity after just one week

About Agentis MCP

What is Agentis MCP: Build AI Agents, Seamless Integration?

Agentis MCP is a flexible framework designed to simplify the creation and management of AI agents. It acts as a bridge between your applications and MCP servers, enabling seamless access to tools, resources, and advanced workflows. Whether you're building a simple chatbot or a complex multi-agent system, this framework handles the heavy lifting so you can focus on what matters most.

Key Features of Agentis MCP

Server Connectivity: Tap into MCP servers for real-time data and tool access with just a few lines of code.
Agent Orchestration: Create dynamic workflows by coordinating multiple agents to handle tasks like data processing or user queries.
User-Friendly API: Build custom agents using an intuitive API that prioritizes simplicity without sacrificing power.
Configurable & Adaptable: Switch between stdio and SSE transport methods, manage persistent vs. temporary connections, and aggregate tools from multiple servers.

Agentis MCP Features

How to Use Agentis MCP

Let’s get hands-on! Here’s the quickstart roadmap:

Install: pip install agentis-mcp
Configure: Set up your MCP server details in a YAML file (like API endpoints or authentication).
Run: Use the async-friendly API to create agents and execute tasks. Check this example:


async def main():
    config = load_config("my-config.yaml")
    context = AgentContext(config)
    async with Agent(context) as agent:
        result = await agent.run("Analyze sales trends in Q3")
        print(result)

Use Cases of Agentis MCP

Imagine these scenarios:

A customer service chatbot pulling live data from multiple tools to resolve issues instantly.
A data analyst automating report generation by stitching together data from internal systems and external APIs.
A research team running complex simulations by distributing tasks across multiple agents.

Agentis MCP FAQ

FAQ from Agentis MCP

Can I connect to multiple MCP servers at once?: Yes! The aggregation feature lets you combine resources from different servers into a single workflow.
What happens if the server goes offline temporarily?: Agentis handles retries and fallbacks automatically thanks to its persistent connection management.
Do I need to write everything from scratch?: Nope! Leverage pre-built agent templates and focus on configuring the parts that matter for your use case.
Where’s the full documentation?: Check the docs folder for tutorials, API references, and troubleshooting guides.

Content

Agentis MCP

A flexible multi-agent framework for building powerful AI agents with MCP server connectivity.

Features

Connect to MCP servers for tool access and resource retrieval
Build multi-agent workflows with powerful orchestration
Simple and intuitive API for creating custom agents
Flexible configuration system
Support for different transport mechanisms (stdio, SSE)
Persistent and temporary connection management
Aggregation of multiple tool servers

Installation

pip install agentis-mcp

Quick Start

import asyncio
from agentis_mcp import Agent, AgentContext
from agentis_mcp.config import load_config

async def main():
    # Load the configuration from a YAML file
    config = load_config("config.yaml")
    
    # Create an agent context
    context = AgentContext(config)
    
    # Create an agent with the context
    async with Agent(context) as agent:
        # Run a task with the agent
        result = await agent.run("What's the weather in San Francisco?")
        print(result)

asyncio.run(main())

Documentation

For detailed documentation, see the docs directory.

License

APACHE 2.0