# Get File Text — Box

> Extracts the text content of a Box file using its extracted_text representation. Works for office documents, presentations, spreadsheets, PDFs, and plain-text or code files. Box does not generate this representation for images (they have…

- Key: `box-get-file-text`
- Type: Action (Read-only)
- Version: 0.0.3
- App: Box (`box`) — https://pipedream.com/apps/box.md
- This page (HTML): https://pipedream.com/apps/box/actions/get-file-text
- Hints: read-only · open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/box/actions/get-file-text/get-file-text.mjs

## Description

Extracts the text content of a Box file using its `extracted_text` representation. Works for office documents, presentations, spreadsheets, PDFs, and plain-text or code files. Box does not generate this representation for images (they have no text layer) or for files larger than 500 MB, and the action fails with an error when the file has no text representation. Use **Download File** to fetch the raw file instead. [See the documentation](https://developer.box.com/guides/representations/text)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `folderId` | `string` | Yes | The folder containing the file to extract text from. Use 0 for the root folder. Use the List Folders action to retrieve folder IDs. Options are loaded from the connected account. |
| `fileId` | `string` | Yes | The file to extract text from (e.g. 123456789). Use the List Folder Items action to retrieve file IDs. Options are loaded from the connected account. |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_PROJECT_ID!,
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "box",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "box-get-file-text",
  arguments: {
    folderId: "Folder",
    fileId: "File",
  },
})
```

**TypeScript**

```ts
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "box-get-file-text",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    box: { authProvisionId: "apn_xxxxxxx" },
    folderId: "Folder",
    fileId: "File",
  },
})

console.log(result)
```

**cURL**

```bash
curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "box-get-file-text",
    "configured_props": {
      "box": { "authProvisionId": "apn_xxxxxxx" },
      "folderId": "Folder",
      "fileId": "File"
    }
  }'
```

---

- App: https://pipedream.com/apps/box.md · All apps: https://pipedream.com/apps