# Why Directly Generating MCP Servers from OpenAPI Schemas Can Be Problematic

DevFeed: [Why Directly Generating MCP Servers from OpenAPI Schemas Can Be Problematic](<https://devfeed.tech/articles/auto-generating-mcp-servers-from-openapi-schemas-yay-or-nay-4999.md>)

Original publisher: [Read original article](<https://neon.com/blog/autogenerating-mcp-servers-openai-schemas>)

Author: David Gomes

Published: 2025-05-01T19:07:18Z

Content type: article

Language: en

Sources: [Blog -- Neon Docs](<https://devfeed.tech/sources/blog-neon-docs.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [OpenAPI Specification](<https://devfeed.tech/topics/openapi.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [API](<https://devfeed.tech/topics/api.md>), [REST API](<https://devfeed.tech/topics/rest-api.md>), [GitHub API](<https://devfeed.tech/topics/github-api.md>), [FastAPI](<https://devfeed.tech/topics/fastapi.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fastapi](<https://devfeed.tech/tags/fastapi.md>), [github](<https://devfeed.tech/tags/github.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [openapi](<https://devfeed.tech/tags/openapi.md>), [product](<https://devfeed.tech/tags/product.md>), [rest-apis](<https://devfeed.tech/tags/rest-apis.md>)

## AI overview

The article examines whether existing REST APIs and OpenAPI schemas should be converted directly into Model Context Protocol servers. It argues that one-to-one generation can overwhelm language models with too many tools and complex JSON parameters, making tool selection unreliable, especially for large or sensitive APIs.

## Source excerpt

Should we be generating Model Context Protocol (MCP) servers directly from existing API specs? MCP is designed to let AI agents like those in Claude, Cursor, and Windsurf interact with tools and APIs. So, can we just treat our existing REST APIs as the interface for LLMs and enti...