OpenAI IntegrationSAFE
Query OpenAI models directly from Claude using MCP protocol.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Query OpenAI models directly from Claude using MCP protocol.
Setup
Add to claude_desktop_config.json:
{
"mcpServers": {
"openai-server": {
"command": "python",
"args": ["-m", "src.mcp_server_openai.server"],
"env": {
"PYTHONPATH": "C:/path/to/your/mcp-server-openai",
"OPENAI_API_KEY": "your-key-here"
}
}
}
}Development
git clone https://github.com/pierrebrunelle/mcp-server-openai cd mcp-server-openai pip install -e .
Testing
# Run tests from project root pytest -v test_openai.py -s # Sample test output: Testing OpenAI API call... OpenAI Response: Hello! I'm doing well, thank you for asking... PASSED
License
MIT License
35e96248d55cOBSERVED · 2026-10-07Connect
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.
claude mcp add mcp-server-openai -- uvx mcp-server-openai
{
"mcpServers": {
"mcp-server-openai": {
"command": "uvx",
"args": [
"mcp-server-openai"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ask-openai | read | Ask my assistant models a direct question |
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.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
35e96248d55cfull audit observations/trust-audit/mcp-server/pierrebrunelle__openai-integration-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 35e96248d55c | SAFE | B | 89 | first audit |
Questions
What is the OpenAI Integration MCP server?
Query OpenAI models directly from Claude using MCP protocol.
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?
No credential environment variables were found in its source, so it appears to need none.
How does OpenAI Integration run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-server-openai.
How current is this page?
The grade is for one exact copy of the source (35e96248d55c), read on 2026-10-07. The repository is watched and re-audited when it changes.