> ## Documentation Index
> Fetch the complete documentation index at: https://docs.promptloop.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Quickstart

> Connect PromptLoop to Cursor, Claude, ChatGPT, or Codex with one-click OAuth — no API keys to paste

PromptLoop ships a remote [Model Context Protocol](https://modelcontextprotocol.io) server so any
MCP-capable AI client can run your research tasks, launch batches, search for companies, and check
usage — all authenticated with OAuth. There is nothing to self-host.

## Server URL

```
https://promptloop.com/mcp
```

The transport is **Streamable HTTP** and auth is **OAuth 2.1** (PKCE + Dynamic Client Registration).
The first time a client connects it opens a browser window where you sign in and approve access. The
connection is scoped to your team and can be revoked anytime from
[API settings](https://promptloop.com/account/settings).

<Note>
  The fastest way to connect is the in-app installer:
  [promptloop.com/mcp/install](https://promptloop.com/mcp/install) has one-click buttons and
  copy-paste configuration for every client.
</Note>

## Connect your client

<Tabs>
  <Tab title="Cursor">
    Add this to `~/.cursor/mcp.json`:

    ```json theme={null}
    {
      "mcpServers": {
        "promptloop": {
          "url": "https://promptloop.com/mcp"
        }
      }
    }
    ```

    Cursor shows a **Needs login** prompt — click it to authorize with OAuth.
  </Tab>

  <Tab title="Claude">
    In Claude (web or desktop): **Settings → Connectors → Add custom connector**, set the URL to
    `https://promptloop.com/mcp`, then click **Connect** and sign in.

    Custom connectors require a paid Claude plan (Pro, Max, Team, or Enterprise).
  </Tab>

  <Tab title="ChatGPT">
    Enable **Settings → Connectors → Advanced settings → Developer mode**. In the Connectors tab
    click **Create**, set the MCP server URL to `https://promptloop.com/mcp`, set Authentication to
    **OAuth**, then create and authorize.
  </Tab>

  <Tab title="Codex">
    ```bash theme={null}
    codex mcp add promptloop --url https://promptloop.com/mcp
    ```

    Restart Codex — a browser window opens for OAuth on the first tool call.
  </Tab>

  <Tab title="Claude Code">
    ```bash theme={null}
    claude mcp add --transport http promptloop https://promptloop.com/mcp
    ```

    Run `/mcp` inside Claude Code and pick `promptloop` to authenticate.
  </Tab>
</Tabs>

## Available tools

| Tool                                                             | What it does                                       |
| ---------------------------------------------------------------- | -------------------------------------------------- |
| `list_tasks`, `get_task`                                         | Discover saved tasks and their inputs/outputs      |
| `run_task`                                                       | Run a saved task on one or more inputs             |
| `run_dynamic_research`                                           | Ad-hoc research on a single website, no saved task |
| `create_task`, `edit_task`, `test_task`                          | Build and refine tasks from natural language       |
| `create_batch`, `list_batches`, `get_batch`, `get_batch_results` | Run and track large async jobs                     |
| `cancel_batch`, `retry_batch`, `set_batch_webhook`               | Manage batches                                     |
| `search_companies`                                               | Find companies matching an ICP and export a CSV    |
| `get_usage`, `get_limits`                                        | Check credit usage and plan limits                 |

## Setup prompt

Paste this into your assistant so it knows how to drive PromptLoop:

```md Prompt template theme={null}
You have access to the PromptLoop MCP server (https://promptloop.com/mcp).

- Use list_tasks to find saved research tasks before creating a new one.
- Use run_task for a saved task, or run_dynamic_research for a one-off website.
- Use create_task / test_task to build and validate a new task.
- Use create_batch for large lists, then get_batch and get_batch_results.
- Use search_companies to build a target list, and get_usage / get_limits to check credits.

Confirm with me before launching large batch jobs.
```

## Revoking access

Every connection is backed by a short-lived, auto-rotating team API key. To disconnect a client,
revoke its key from [API settings](https://promptloop.com/account/settings) — the client will stop
working immediately.