Code Interpreter API
CAUTIONgrade B · trust 83/100👾 Open source implementation of the ChatGPT Code Interpreter
chatgptchatgpt code generationcode interpretercodeinterpreterlangchainllm agentOverview
From the repository's own README, as read at the audited commit.
# 👾 Code Interpreter API[](https://badge.fury.io/py/codeinterpreterapi)A [LangChain](https://github.com/langchain-ai/langchain) implementation of the ChatGPT Code Interpreter.Using CodeBoxes as backend for sandboxed python code execution.[CodeBox](https://github.com/shroominic/codebox-api/tree/main) is the simplest cloud infrastructure for your LLM Apps.You can run everything local except the LLM using your own OpenAI API Key.## Features- Dataset Analysis, Stock Charting, Image Manipulation, ....- Internet access and auto Python package installation- Input `text + files` -> Receive `text + files`- Conversation Memory: respond based on previous inputs- Run everything local except the OpenAI API (OpenOrca or others maybe soon)- Use CodeBox API for easy scaling in production## DocsCheckout the [documentation](https://shroominic.github.io/codeinterpreter-api/) for more information.## InstallationGet your OpenAI API Key [here](https://platform.openai.com/account/api-keys) and install the package.```bashpip install "codeinterpreterapi[all]"```Everything for local experiments are installed with the `all` extra.For deployments, you can use `pip install codeinterpreterapi` instead which does not install the additional dependencies.## UsageTo configure OpenAI and Azure OpenAI, ensure that you set the appropriate environment variables (or use a .env file):For OpenAI, set the OPENAI_API_KEY environment variable:```bashexport OPENAI_API_KEY=sk-**********``````pythonfrom codeinterpreterapi import CodeInterpreterSession, settings# create a session and close it automaticallywith CodeInterpreterSession() as session: # generate a response based on user input response = session.generate_response( "Plot the bitcoin chart of
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.
claude mcp add codeinterpreterapi -- uvx codeinterpreterapi
{
"mcpServers": {
"codeinterpreterapi": {
"command": "uvx",
"args": [
"codeinterpreterapi"
]
}
}
}Exposed tools (1) 1 read · 0 write · 0 destructive
| Tool | Risk | Description |
|---|---|---|
python | read | Input a string of code to a ipython interpreter. |
Details
- Source
- shroominic/codeinterpreter-api
- PyPI
codeinterpreterapi- License
- MIT
- Stars
- 3,846 · pushed 676d ago
Trust audit
Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (5)
POSTGRES_URL: str = "postgresql://postgres:postgres@localhost:5432/postgres"
- `POSTGRES_URL: str = "postgresql://postgres:postgres@localhost:5432/postgres"`
file_buffer = BytesIO(base64.b64decode(output.content))
file_buffer = BytesIO(base64.b64decode(output.content))
- Get your API key from [CodeBox](https://pay.codeboxapi.com/b/00g3e6dZX2fTg0gaEE) (you get an email with the api-key)
Gates applied: no_behavioural_pass.
Audited 2026-09-14 · audit v0.4.0 · source sha b7708f9f9882 · full audit: observations/trust-audit/mcp-server/shroominic__code-interpreter-api.json · Report an issue or request a re-scan
Audit history
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-14 | b7708f9f9882 | CAUTION | B | 83 | first audit |
Alternatives
Other servers in the same categories, safer ones first.
Questions
What is the Code Interpreter API MCP server?
👾 Open source implementation of the ChatGPT Code Interpreter
What tools does Code Interpreter API 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 Code Interpreter API safe to connect to an agent?
With care. The audit graded it B (83/100) and found 5 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Code Interpreter API need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (b7708f9f9882), read on 2026-09-14. The repository is watched and re-audited when it changes.
Provenance: OBSERVED · read 2026-09-14 · job trust-audit-2026-09-14