mcpbeat Sign in

mcpify MCP Server

local only

mcpify runs on your own machine — the client starts it, so there is no endpoint to ping. 12 627 installs a week from pypi. Last commit 31 Aug 2026.

Focused, production-ready CLI: turn any OpenAPI REST API into an MCP server.

12 627
Installs / week
pypi · mcpify-openapi
2
Stars
0 open issues
31 Aug 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 14 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

    return yaml.load(path.read_text(encoding="utf-8"), Loader=loader) or {}  # noqa: S506 — safe loaders only

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add mcpify -- uvx mcpify-openapi
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcpify": {
      "args": [
        "mcpify-openapi"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcpify]
command = "uvx"
args = ["mcpify-openapi"]
.cursor/mcp.json
{
  "mcpServers": {
    "mcpify": {
      "args": [
        "mcpify-openapi"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcpify": {
      "args": [
        "mcpify-openapi"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to mcpify

same job, measured the same way
FAQai
by faqai

Turn any document into a production-ready RAG dataset from Claude, Cursor, or any MCP host.

65 installs/wk local only
Agentify
by sani-savaliya

Turn any OpenAPI/Swagger spec into an MCP server - every API operation becomes an agent tool.

49 installs/wk local only
Pylos MCP
by adamvass

Read-focused, prompt-injection-hardened email MCP server for any IMAP provider

71 installs/wk local only
MCP Shopify
by codespar

MCP server for Shopify — Admin REST API (orders, products, customers, inventory, fulfillments)

39 installs/wk local only
PDF MCP
by jztan

Production-ready MCP server for PDF processing with intelligent caching.

1 772 installs/wk local only
AWS CLI MCP Server
by musaddiq-dev

Python MCP server for AWS CLI inspection and operations

81 installs/wk local only
PensionPro
by douglaslinsmeyer

MCP server for the PensionPro pension administration REST API.

62 installs/wk local only
MCP Openapi
by infoinlet-marketplace

Turn any OpenAPI/Swagger spec into MCP tools — each operation an SSRF-guarded tool.

39 installs/wk local only

mcpify — questions

Answers built from our own checks of this server.

Why is there no uptime for mcpify?
mcpify runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcpify-openapi was installed 12 627 times last week.
How do I connect mcpify?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mcpify-openapi straight from pypi; nothing to host, nothing to sign up for.
How many people use mcpify?
The pypi package mcpify-openapi was installed 12 627 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is mcpify open source?
Yes — it is published under the MIT licence, written in Python and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.