# Use Agentailor with AI: Skills, MCP & Prompts

Give your coding agent practical guidance, let your assistant search the articles and repo docs, or try a prompt with an assistant that can read the web.

## Choose your starting point

- [Install skills](https://agentailor.com/for-agents#skills): Design tools, write agent instructions, or build eval cases.
- [Connect via MCP](https://agentailor.com/for-agents#mcp): Search Agentailor articles and read public repo docs as you work.
- [Try a prompt](https://agentailor.com/for-agents#prompts): Explore the guides with an assistant that can fetch web pages.

## Install skills

Skills give your coding agent reusable guidance for a specific task. MCP gives it access to articles and repo docs. You can use both together.

- [Tool Design](https://agentailor.com/skills#tool-design): Clearer tool definitions, focused outputs, and a checklist to review them.
- [Agent Prompt Engineering](https://agentailor.com/skills#agent-prompt-engineering): Instructions with clearer decisions, boundaries, and stopping conditions.
- [Agent Eval Cases](https://agentailor.com/skills#agent-eval-cases): Focused cases with appropriate graders, based on failures you have actually seen.

Installation and example tasks: https://agentailor.com/skills.md

## Connect via MCP

For ongoing access to Agentailor articles and public repo docs, connect your assistant over the Model Context Protocol. It can search for relevant guides and read them as needed.

Use a client that can run a local MCP server, with Node.js 20 or newer and npx available. Public content needs no API key. Merge the entry into your existing config if you already have other servers.

### Claude Code

Run from your project directory. Check the connection with /mcp inside Claude Code.

Config / command: terminal

```sh
claude mcp add agentailor -- npx -y @agentailor/mcp
```

### Claude Desktop

Settings › Developer › Edit Config, then restart Claude Desktop.

Config / command: claude_desktop_config.json

```json
{
  "mcpServers": {
    "agentailor": {
      "command": "npx",
      "args": [
        "-y",
        "@agentailor/mcp"
      ]
    }
  }
}
```

### Cursor

Create .cursor/mcp.json in your project (or ~/.cursor/mcp.json for all projects).

Config / command: .cursor/mcp.json

```json
{
  "mcpServers": {
    "agentailor": {
      "command": "npx",
      "args": [
        "-y",
        "@agentailor/mcp"
      ]
    }
  }
}
```

### VS Code / Copilot

Create .vscode/mcp.json in your workspace. The top-level key is servers.

Config / command: .vscode/mcp.json

```json
{
  "servers": {
    "agentailor": {
      "command": "npx",
      "args": [
        "-y",
        "@agentailor/mcp"
      ]
    }
  }
}
```

### OpenAI Codex

Add this entry to ~/.codex/config.toml.

Config / command: ~/.codex/config.toml

```toml
[mcp_servers.agentailor]
command = "npx"
args = ["-y", "@agentailor/mcp"]
```

### Other

For other clients that support local stdio servers, use this command.

Config / command: stdio command

```sh
npx -y @agentailor/mcp
```

### Check the connection

Once the client shows the server as connected, try this. Expect article links and a repo list.

Use the Agentailor MCP tools to find articles about tool design, read the most relevant one, and list the public Agentailor repos. Include source links and tell me if any tool call fails.

More setup options and troubleshooting: https://github.com/agentailor/mcp

Hosted MCP is planned. For now, use the local setup on this page; a hosted endpoint URL is not available yet.

## Try a prompt

Use an assistant that can fetch web pages. Start with the index, then read relevant articles.

Read https://blog.agentailor.com/llms.txt. I'm new to building AI agents. Choose and read three articles that will help me get started, explain the order, and suggest one small project I can build next. Link to each source.

### Plan four weeks

Read https://blog.agentailor.com/llms.txt and the relevant articles and open-source repo docs. Design a structured four-week curriculum for a developer new to AI agents. Order the readings from fundamentals to production, link to the sources, and tell me what to build each week.

### Decide my path

Read https://agentailor.com/paths.md and the four path pages it links to. I'm a solo founder who wants to ship fast but keep control of the architecture. Walk me through the four ways to build an agent, then recommend one with the trade-offs I'd be accepting.

### Compare stacks

Use https://blog.agentailor.com/llms.txt to find and read the articles about AI agent frameworks. Compare them for a TypeScript team building an MCP-based agent and recommend a stack. Cite the articles behind each recommendation and flag gaps in the available evidence.

### Build an MCP server

Find Agentailor's agent roadmap and MCP guides in https://blog.agentailor.com/llms.txt. Read them and the create-mcp-server repo docs from https://github.com/agentailor/create-mcp-server. Give me a step-by-step plan to build and deploy my first MCP server this weekend, linking each step to its source.

### Prepare for production

Find and read Agentailor's articles on evaluation, observability, and standards using https://blog.agentailor.com/llms.txt. Explain what to check before shipping my first agent, which checks to do first, and where to read deeper. Cite sources and distinguish the articles' guidance from your own suggestions.

## Read the content directly

### llms.txt — start with an index

- https://agentailor.com/llms.txt
- https://blog.agentailor.com/llms.txt

### Markdown pages

These pages and each individual path have a Markdown version. For blog articles, follow the Markdown URLs in the blog index.

- [Skills](https://agentailor.com/skills.md)
- [Use with AI](https://agentailor.com/for-agents.md)
- [The four paths](https://agentailor.com/paths.md)
- [What is an agent](https://agentailor.com/what-is-an-agent.md)
- [Glossary](https://agentailor.com/glossary.md)

### llms-full.txt — expanded index

An expanded content index with article summaries, metadata, and series context. Follow the linked Markdown URLs to read the articles in full.

https://blog.agentailor.com/llms-full.txt

```sh
curl https://agentailor.com/skills.md
```

New to building agents? Read https://agentailor.com/what-is-an-agent and https://agentailor.com/paths.

---
Source: https://agentailor.com/for-agents