AI CLI MCP Server

@tryAGI

代码仓库

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

tryAGI

关于 AI CLI MCP Server

AI in your terminal — powered by agents and MCP

#agent #cli #ai #command-line #mcp #openai #openrouter #mcp-server

AI CLI MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

AI CLI MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is AI CLI?

AI CLI is a console utility that brings AI into your terminal, powered by agents and MCP (Model Context Protocol). It helps developers automate tasks like summarizing text, generating release notes, changelogs, code documentation, and executing actions via MCP servers.

How to use AI CLI?

Install globally with dotnet tool install --global tryagi.ai --prerelease. Set the OPENAI_API_KEY environment variable, then run AI CLI with appropriate flags (e.g., --tools, --provider, --model, --input). See the README for detailed examples, including filesystem/git operations and GitHub issue auto-labelling.

Key features of AI CLI

Summarize text and generate release notes.
Generate changelogs and code documentation.
Perform filesystem and git actions using MCP servers.
Auto-label GitHub issues with configurable prompts.
Supports multiple providers (e.g., OpenRouter) and models.
Input via command-line (--input) or prompt file (--input-file).

Use cases of AI CLI

Quickly summarize long text passages in the terminal.
Generate release notes and changelogs from git history.
Create code documentation for existing codebases.
Automate GitHub issue labelling based on issue content.
Set up and initialize new git repositories with AI guidance.

常见问题

What dependencies does AI CLI require?

It requires the .NET SDK to install the global tool via `dotnet tool`. An OpenAI API key (`OPENAI_API_KEY`) must be set as an environment variable.

Where does data processed by AI CLI reside?

Data is processed locally from your filesystem and git repositories. For GitHub actions, data is retrieved from the GitHub API. No data is stored externally by the tool.

What transports and authentication methods does AI CLI support?

AI CLI uses MCP for tool interactions. Authentication is handled via API keys (e.g., `OPENAI_API_KEY` for OpenAI/OpenRouter, `GITHUB_TOKEN` for GitHub operations).

Can I use AI CLI with models other than OpenAI?

Yes, the `--provider openrouter` flag and `--model free-fast` example show support for alternative providers. Any provider compatible with the OpenAI API format should work.

What are the known limitations of AI CLI?

The README does not specify explicit limitations. It is a console utility and requires a .NET runtime environment. Feature requests and bugs should be reported on the GitHub issues page.

开发工具分类下的更多 MCP 服务器

offprompt

MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Zyte MCP

Zyte

Zyte MCP is a remote MCP server available at https://mcp.zyte.com/v1/mcp/, that lets an agent use Zyte on your behalf: to get web pages, to extract data from them, to search the web, and to work with your Scrapy Cloud pr

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.