# Cline on Codex Pooler

Cline is an open-source coding agent that can inspect a project, edit files and run commands as part of a task. This guide connects Cline CLI to Codex Pooler, so you can use your Pool's models for interactive coding or automated runs.

![Codex Pooler Cline integration](/codex-pooler-cline.webp)

## Before you start

- Install [Cline CLI](https://docs.cline.bot/getting-started/installing-cline) using the official instructions for your operating system.
- Have a Codex Pooler URL reachable from the client.
- Create a [Pool API key](/getting-started/quick-start/) and choose a model available to that Pool.

## Configure the connection

Cline CLI accepts `openai` as shorthand for its OpenAI-compatible provider and stores it as `openai-compatible`.

Use the commands for the terminal that starts the client. Environment-variable assignments below apply to that terminal; desktop apps and services need the variables in their own launch environment.

Run the following command in a shell with `CODEX_POOLER_API_KEY` set to your Pool API key:

**macOS / Linux / WSL**

```bash
cline auth \
  --provider openai \
  --apikey "$CODEX_POOLER_API_KEY" \
  --baseurl https://codex-pooler.example.com/v1 \
  --modelid gpt-6-sol
```

**Windows PowerShell**

```powershell
cline auth --provider openai --apikey "$env:CODEX_POOLER_API_KEY" --baseurl https://codex-pooler.example.com/v1 --modelid gpt-6-sol
```

For local setup, change `--baseurl` to `http://localhost:4000/v1`.

## Choose a model

Use `--modelid` above to select a model available to your Pool.

Cline's user-facing model metadata names are `contextWindow`, `maxInputTokens`, and `maxTokens`. A long-profile example uses `contextWindow: 828400`, `maxInputTokens: 700400`, and `maxTokens: 128000` for a model whose selected Pool catalog source reports an 872000-token raw ceiling. Provider accounts can temporarily report different ceilings for the same model; a selected 272000-token profile exposes `258400`, so use `/v1/models.context_length` as the authoritative `contextWindow` and adjust the input budget rather than configuring a raw ceiling. In the long-profile example, Cline applies its fixed 90% compaction ratio to the explicit input limit and starts compaction at 630360 tokens. `maxTokens` remains a separate response cap.

## Verify the connection

Check the headless CLI path after saving auth:

**macOS / Linux / WSL**

```bash
cline --provider openai \
  --model gpt-6-sol \
  --json \
  --auto-approve false \
  'Reply with exactly: cline ok'
```

**Windows PowerShell**

```powershell
cline --provider openai --model gpt-6-sol --json --auto-approve false 'Reply with exactly: cline ok'
```

In Codex Pooler's request logs, match the request time, API key, model, and final status to your test. A reply alone does not confirm that the client used your Pooler instance.

## Operator MCP (optional)

For optional operator MCP in Cline CLI, add the remote server to `mcp.json` at the path for your system:

| OS | Default config file |
| --- | --- |
| macOS | `~/.cline/mcp.json` |
| Linux | `~/.cline/mcp.json` |
| Windows | `%USERPROFILE%\.cline\mcp.json` |

These are the default locations. On Windows, paste the `%USERPROFILE%`, `%APPDATA%` or `%LOCALAPPDATA%` path into File Explorer's address bar. For a client installed inside WSL, use the Linux paths and commands inside WSL. Keep any custom configuration folder or profile you already use.

Codex Pooler does not require this for model use. The VS Code extension opens its own MCP settings JSON from the Cline MCP Servers panel; use the same `mcpServers` shape there.

```json title="mcp.json" frame="code"
{
  "mcpServers": {
    "codex_pooler": {
      "url": "https://codex-pooler.example.com/mcp",
      "headers": {
        "Authorization": "Bearer <operator-mcp-token>"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}
```

For local MCP setup, change the MCP `url` to `http://localhost:4000/mcp`.

Use a Pool API key for `/v1` model requests and an operator MCP token for `/mcp`. Do not reuse the Pool API key for MCP.

## Compatibility notes

This client uses Codex Pooler's narrow OpenAI-compatible `/v1` surface. For shared route support and limits, see [OpenAI-compatible SDKs](/clients/openai-compatible/).