Agentis MCP

Source

Python framework for creating AI agents that use MCP servers as tools. Compatible with any MCP server and model provider.

Catalog onlyCatalog onlySTDIO

Overview

Agentis MCP is a Python framework designed for creating AI agents that utilize MCP servers as tools, enabling flexible multi-agent workflows.

To use Agentis MCP, install the package via pip and create an agent using the provided API. Load your configuration and run tasks with the agent in an asynchronous context.

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

Developing AI agents for data retrieval and processing
Creating automated workflows that involve multiple tools
Building custom agents for specific tasks using MCP servers

Add to your AI client

Use these steps to connect Agentis MCP in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-agentis-agentislabs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-agentis-agentislabs"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-agentis-agentislabs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-agentis-agentislabs"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-agentis-agentislabs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-agentis-agentislabs"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-agentis-agentislabs": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-agentis-agentislabs"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-agentis-agentislabs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-agentis-agentislabs"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-agentis-agentislabs": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-agentis-agentislabs"
      ]
    }
  }
}

FAQ

What programming language is Agentis MCP built with?

Agentis MCP is built with Python.

How do I install Agentis MCP?

You can install it using the command: `pip install agentis-mcp`.

Can I use Agentis MCP with any MCP server?

Yes! Agentis MCP is compatible with any MCP server and model provider.

Developer tools