Codex can use Impulse through the Model Context Protocol (MCP). Once connected, Codex can upload datasets, start training sessions, inspect artifacts, deploy models, and run predictions through the Impulse tools.
This guide is for Codex only. For direct REST API calls, see the Quickstart.
Requirements
- A Codex app or Codex CLI install.
- An Impulse account with access to the production dashboard.
- A browser session that can sign in to Impulse during MCP OAuth.
You do not need to copy an Impulse API key into Codex when using the OAuth MCP setup below. Codex stores the MCP server config locally and completes auth through your browser.
Connect Codex from settings
The Codex app, CLI, and IDE extension share MCP settings. If you connect Impulse in one Codex surface, the others can use the same server because the configuration is stored in config.toml.
Open Codex settings
In the Codex app, open Settings from the app menu or press Cmd+, on macOS.
Open Integrations & MCP
Go to Integrations & MCP. This is where Codex manages external MCP servers.
Add a custom MCP server
Choose the option to add your own MCP server.
Enter the server details
Use impulse as the server name and https://api.impulselabs.ai/api/mcp-http as the server URL.
Authenticate
If Codex prompts for OAuth, continue in the browser, sign in to Impulse, approve access, and return to Codex.
Start a new thread
Open a new Codex thread and ask Codex to use Impulse.
Connect Codex from the CLI
If you prefer terminal setup, add the same production Impulse MCP server with the Codex CLI:
codex mcp add impulse --url https://api.impulselabs.ai/api/mcp-http
impulse MCP server with available Impulse tools.
Optional local config
Codex stores MCP servers in ~/.codex/config.toml. The CLI command above writes a config similar to:
[mcp_servers.impulse]
url = "https://api.impulselabs.ai/api/mcp-http"
.codex/config.toml inside a trusted project.
First Codex prompt
After auth, start a new Codex thread and ask it to use Impulse:
Use the Impulse MCP server to train a model from my uploaded dataset. Show me the session id, required artifacts, metrics, and prediction file when the run is complete.
Use Impulse MCP. Train a tabular classification model with dataset_id=<TRAIN_DATASET_ID> and test_dataset_id=<TEST_DATASET_ID>. The target column is Transported. Produce submission.csv and save the canonical model artifacts.
What Codex can do
Once connected, Codex can use Impulse MCP tools to:
- Upload datasets.
- List datasets and projects.
- Start training sessions.
- Poll session status.
- Inspect generated artifacts.
- Package models for inference.
- Deploy trained models.
- Fetch deployment feature contracts.
- Run predictions against deployed models.
Troubleshooting
Codex says the server is not authenticated
Run the login command again:
Then start a new Codex thread. New MCP auth and tool availability are easiest to verify in a fresh thread.
The OAuth callback fails
Make sure the production Impulse Auth0 application allows the callback URL used by Codex. Codex may use a localhost callback URL by default unless you configure a custom callback URL.
Check the server list:
If the server is missing, add it again:
codex mcp add impulse --url https://api.impulselabs.ai/api/mcp-http
codex mcp login impulse
