ModelsAtlas
Explore
Atlas / MCP servers / mzxrai / Openai Integration

Openai IntegrationSAFE

mcp/mzxrai/openai-integration
MCP server by mzxrai · Audited 2026-10-07
⚑ Report / re-scanSource ↗

Chat with OpenAI models from Claude Desktop

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
1 1r · 0w · 0d
Transport
stdio
License
MIT
Stars
77
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server that lets you seamlessly use OpenAI's models right from Claude.

Features

  • Direct integration with OpenAI's chat models
  • Support for multiple models including:
  • gpt-4o
  • gpt-4o-mini
  • o1-preview
  • o1-mini
  • Simple message passing interface
  • Basic error handling

Prerequisites

Installation

First, make sure you've got the Claude Desktop app installed and you've requested an OpenAI API key.

Add this entry to your claude_desktop_config.json (on Mac, you'll find it at ~/Library/Application\ Support/Claude/claude_desktop_config.json):

{
"mcpServers": {
"mcp-openai": {
"command": "npx",
"args": ["-y", "@mzxrai/mcp-openai@latest"],
"env": {
"OPENAI_API_KEY": "your-api-key-here (get one from https://platform.openai.com/api-keys)"
}
}
}
}

This config lets Claude Desktop fire up the OpenAI MCP server whenever you need it.

Usage

Just start chatting with Claude and when you want to use OpenAI's models, ask Claude to use them.

For example, you can say,

Can you ask o1 what it thinks about this problem?

or,

What does gpt-4o think about this?

The server currently supports these models:

  • gpt-4o (default)
  • gpt-4o-mini
  • o1-preview
  • o1-mini

Tools

  1. openai_chat
  2. Sends messages to OpenAI's chat completion API
  3. Arguments:
  4. messages: Array of messages (required)
  5. model: Which model to use (optional, defaults to gpt-4o)

Problems

This is alpha software, so may have bugs. If you have an issue, check Claude Desktop's MCP logs:

tail -n 20 -f ~/Library/Logs/Claude/mcp*.log

Development

# Install depen
Read from source at commit d1b83ef623fbOBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add mcp-openai --env OPENAI_API_KEY=${OPENAI_API_KEY} -- npx -y @mzxrai/[email protected]
claude-desktop
{
  "mcpServers": {
    "mcp-openai": {
      "command": "npx",
      "args": [
        "-y",
        "@mzxrai/[email protected]"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
03

Exposed tools (1)

1 read · 0 write · 0 destructive.

ToolRiskDescription
openai_chatreadUse this tool when a user specifically requests to use one of OpenAI
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (3)

LOWInventory / provenance · inv.hidden_file · CWE-1104
.gitmodules
.gitmodules
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
openai, shx, tsx, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427
docs/mcp_spec/llms-full.txt:2197
# Load environment variables
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha d1b83ef623fbfull audit observations/trust-audit/mcp-server/mzxrai__openai-integration.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07d1b83ef623fbSAFEB89first audit
06

Questions

What is the Openai Integration MCP server?

Chat with OpenAI models from Claude Desktop

What tools does Openai Integration expose?

1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Openai Integration safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Openai Integration need?

It reads OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Openai Integration run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @mzxrai/mcp-openai at 0.1.1.

How current is this page?

The grade is for one exact copy of the source (d1b83ef623fb), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement