CodeInterpreter extends Python-based coding environments with integrated data analysis, enabling developers to run scripts, visualize results, and prototype solutions inside supported platforms
CodeInterpreter extends Python-based coding environments with integrated data analysis, enabling developers to run scripts, visualize results, and prototype solutions inside supported platforms On Nagent, Code Interpreter is exposed as a fully-configurable developer tools integration that any agent can call — 5 actions, and no authentication authentication. No code is required to wire Code Interpreter into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Code Interpreter to automate the kinds of tasks developer tools teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Code Interpreter into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Code Interpreter, with input parameters and output schema. Drop these into any step of an agent built in Helix.
CODEINTERPRETER_CREATE_SANDBOXCreate a sandbox to execute python code in a Jupyter notebook cell. This is useful for agents to communicate, execute code, see output, read files, write files, etc. It's like you own personal computer, but in the cloud. Use /home/user folder to write/read files.
Input parameters
The number of seconds to keep the sandbox alive after creation. Default is 300 seconds (5 minutes). Can be in between 0 and 3600.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CODEINTERPRETER_EXECUTE_CODEExecute python code in a sandbox and return any result, stdout, stderr, and error. Use /home/user folder to write/read files. Try to not use plt.show() as the code is executed remotely. Use files for image/chart output instead.
Input parameters
The timeout in seconds for the execution of the code.
The number of seconds to keep the sandbox alive after execution. Default is 300 seconds (5 minutes). Can be between 0 and 3600.
The ID of the sandbox to execute the code in. Try to find an existing sandbox ID from context in order to access the previous modification session. In case not found, this value might be omitted, a new sandbox will be created.
The python code to execute in a single cell. If a file is to be saved, it should be saved under /home/user/ directory. At the end of the code, a success message print is good to have.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CODEINTERPRETER_GET_FILE_CMDGet a file from the sandbox and returns the file. The files should be read from /home/user folder.
Input parameters
The timeout in seconds for the command to run.
The path(on the sandbox) of the file to get. Give absolute path. Should start with /home/user/
The ID of the sandbox where the file has been created.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CODEINTERPRETER_RUN_TERMINAL_CMDRun a command in the terminal and returns the stdout, stderr, and error code. Use /home/user folder to write/read files.
Input parameters
The command to run in the terminal.
The timeout in seconds for the command to run.
The number of seconds to keep the sandbox alive after execution. Default is 300 seconds (5 minutes).
The ID of the sandbox to execute the code in. Try to find an existing sandbox ID from contextinorder to access the previous modification session. In case not found, this value might be omitted, a new sandbox will be created.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CODEINTERPRETER_UPLOAD_FILE_CMDUpload a file to the sandbox environment. The files should be uploaded to the /home/user folder.
Input parameters
The file to upload, containing the file name and base64-encoded content.
Whether to overwrite the file if it already exists.
The ID of the sandbox where the file will be uploaded.
The destination path in the sandbox where the file will be saved. Provide an absolute path starting with /home/user/. The file name from 'file' will be appended if destination_path is a directory.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 99 agents privately built on Nagent that already use Code Interpreter.
Build on Nagent
Connect Code Interpreter to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Code Interpreter, and click "Connect Now." You'll authenticate with no authentication (it’s public) — Nagent handles credential storage and refresh automatically. Once connected, Code Interpreter is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Code Interpreter is connected, you configure its 5 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Code Interpreter steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Code Interpreter event fires, the agent kicks off automatically.
Every Code Interpreter action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Code Interpreter ships with 5 pre-built developer tools actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Code Interpreter together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Code Interpreter-based workflows tailored to your business.