Agentify

v1.0.0Coding Agentsstable

Agent Interface Compiler — One command. Every agent speaks your product. Transform OpenAPI specs into MCP Servers, Skills, CLAUDE.md, AGENTS.md, and more.

a2aagentagent-nativeagents-mdai
Share:
26
Stars
0
Downloads
0
Weekly
0/5

What is Agentify?

Agentify is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to agent interface compiler — one command. every agent speaks your product. transform openapi specs into mcp servers, skills, claude.md, agents.md, and more.

Agent Interface Compiler — One command. Every agent speaks your product. Transform OpenAPI specs into MCP Servers, Skills, CLAUDE.md, AGENTS.md, and more.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Agent Interface Compiler — One command. Every agent speaks y

Use Cases

Compile OpenAPI to agents
Agent-native servers
Automated AGENTS.md
MonadWorks

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 18, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx agentify

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Agentify

Agentify is an Agent Interface Compiler that transforms OpenAPI 2.0 and 3.x specifications into up to nine agent-ready output formats in a single command — including MCP servers (with Dockerfile), CLAUDE.md, AGENTS.md, .cursorrules, llms.txt, GEMINI.md, A2A Cards, Skills, and a standalone CLI. It auto-detects authentication schemes, domain groupings, and API scale from the spec, so every major AI coding assistant can immediately understand and call your API without manual integration work. API teams and developers use it to make their services instantly accessible to Claude, ChatGPT, Copilot, Cursor, and Gemini without writing boilerplate.

Prerequisites

  • Node.js 18 or later installed
  • npx available on your PATH
  • An OpenAPI 2.0 (Swagger) or OpenAPI 3.x specification file (YAML or JSON), or a public spec URL
  • An MCP-compatible client to use the generated MCP server
1

Run Agentify on your OpenAPI spec

Use npx to run agentify-cli directly without installing it globally. Pass your spec file path or URL as the argument.

npx agentify-cli transform ./my-api.yaml
2

Generate only specific output formats

Use the -f flag to select which output formats to generate. This is useful when you only need an MCP server and CLAUDE.md, for example.

npx agentify-cli transform ./my-api.yaml -f mcp claude.md agents.md
3

Specify an output directory and project name

Use -o to set the output directory and -n to name the project. By default output goes to the current directory.

npx agentify-cli transform ./my-api.yaml -o ./agent-output -n my-project
4

Transform a public Swagger spec

Agentify can fetch and process public OpenAPI specs directly from a URL.

npx agentify-cli transform https://petstore.swagger.io/v2/swagger.json
5

Use the generated MCP server

After generation, the output directory contains an MCP server with a Dockerfile. Configure your MCP client to run it, or build the Docker image for deployment.

{
  "mcpServers": {
    "my-api": {
      "command": "node",
      "args": ["./agent-output/mcp/server.js"]
    }
  }
}

Agentify Examples

Client configuration

Run agentify-cli to generate an MCP server from your API spec, then connect Claude Desktop to it.

{
  "mcpServers": {
    "my-generated-api": {
      "command": "node",
      "args": ["./agent-output/mcp/server.js"]
    }
  }
}

Prompts to try

Example prompts after connecting the generated MCP server to an AI assistant.

- "Generate an MCP server and CLAUDE.md from my OpenAPI spec at ./api/openapi.yaml"
- "Transform the Petstore API spec into all supported agent formats"
- "Create an AGENTS.md and .cursorrules file from my Swagger spec so Cursor and Copilot can use my API"
- "Build a standalone CLI from my OpenAPI spec so I can call the API from the terminal"

Troubleshooting Agentify

Spec parsing fails with 'invalid OpenAPI specification' error

Validate your spec first using a tool like 'npx @redocly/cli lint ./my-api.yaml'. Agentify supports OpenAPI 2.0 and 3.x — ensure your file uses one of these versions and is syntactically valid YAML or JSON.

Generated MCP server does not include all API endpoints

Agentify groups endpoints by domain and may filter or aggregate operations for large specs. Check the generation summary output for warnings about skipped endpoints, and consider splitting very large specs by domain.

Authentication not configured in the generated output

Agentify auto-detects auth from the spec's securitySchemes. If your spec defines API key auth, the generated server will reference it (e.g. as an env var). Ensure your OpenAPI spec explicitly declares the security scheme at the root level and references it on the relevant operations.

Frequently Asked Questions about Agentify

What is Agentify?

Agentify is a Model Context Protocol (MCP) server that agent interface compiler — one command. every agent speaks your product. transform openapi specs into mcp servers, skills, claude.md, agents.md, and more. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Agentify?

Follow the installation instructions on the Agentify GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Agentify?

Agentify works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Agentify free to use?

Yes, Agentify is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "agentify": { "command": "npx", "args": ["-y", "agentify"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Agentify?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides