Aenvironment
Standardized environment infrastructure for Agentic AI development.
What is Aenvironment?
Aenvironment is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to standardized environment infrastructure for agentic ai development.
Standardized environment infrastructure for Agentic AI development.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Standardized environment infrastructure for Agentic AI devel
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx aenvironmentConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Aenvironment
AEnvironment is a standardized infrastructure framework for agentic AI development that provides reproducible, sandboxed environments through the MCP protocol. It ships with built-in environments for reinforcement learning experiments (TAU2), terminal command execution (Mini Terminal), and evaluation benchmarks (TerminalBench), and lets developers define custom environments with callable tools and reward functions. Research teams and AI engineers use it to ensure consistent agent evaluation across machines and to benchmark agentic systems under controlled conditions.
Prerequisites
- Python 3.9 or higher with pip installed
- An MCP client such as Claude Desktop or Claude Code CLI
- Optional: Claude Code CLI for the Deploy Skill integration
- Sufficient disk space for environment dependencies (varies by built-in environment)
Install aenvironment via pip
Install the core package from PyPI. This provides the aenv CLI and the Python library.
pip install aenvironmentInstall the Deploy Skill for Claude Code (optional)
Download and install the AEnvironment Deploy Skill to use environment management commands directly from Claude Code.
curl -L https://github.com/inclusionAI/AEnvironment/releases/latest/download/aenvironment-deploy.skill -o aenvironment-deploy.skill
claude skill install aenvironment-deploy.skillBuild and push a custom environment (optional)
If you have defined a custom environment, build and register it using the aenv CLI.
aenv build && aenv pushAdd the MCP server to your client config
Register the AEnvironment MCP server in your Claude Desktop or other MCP client configuration so tools like search_code, read_file, and write_file are available.
Connect to an environment from Python
Use the Python async API to connect to a named environment, list available tools, call tools, and compute rewards.
import asyncio
from aenv import Environment
async def main():
async with Environment("mini-terminal") as env:
tools = await env.list_tools()
result = await env.call_tool("run_command", {"command": "ls -la"})
print(result)
asyncio.run(main())Aenvironment Examples
Client configuration
Claude Desktop config block for the AEnvironment MCP server.
{
"mcpServers": {
"aenvironment": {
"command": "python",
"args": ["-m", "aenvironment.mcp_server"]
}
}
}Prompts to try
Use AEnvironment tools to run agent benchmarks and manage sandboxed environments.
- "List all available tools in the mini-terminal environment."
- "Run the TerminalBench evaluation suite and report the results."
- "Search the codebase inside the swe-env environment for the string 'def solve'."
- "Register a new custom environment from my local config and verify the reward function."
- "What built-in AEnvironment environments are available?"Troubleshooting Aenvironment
aenv command not found after pip install
Ensure the Python scripts directory is on your PATH. Try running `python -m aenvironment` instead, or check `pip show aenvironment` to confirm installation.
Environment connection times out
Some built-in environments (e.g. TAU2) may require additional dependencies or Docker. Check the repository README for environment-specific requirements and ensure all prerequisites are installed.
Custom reward function not being called
Ensure your reward function is decorated with @register_reward and that the environment is registered before calling aenv build. Check the AEnvironment logs for registration errors.
Frequently Asked Questions about Aenvironment
What is Aenvironment?
Aenvironment is a Model Context Protocol (MCP) server that standardized environment infrastructure for agentic ai development. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Aenvironment?
Follow the installation instructions on the Aenvironment GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Aenvironment?
Aenvironment works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Aenvironment free to use?
Yes, Aenvironment is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Aenvironment Alternatives — Similar Developer Tools Servers
Looking for alternatives to Aenvironment? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Aenvironment in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Aenvironment?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.