---
canonical_url: "https://docs.composio.dev/toolkits/parsio"
markdown_url: "https://docs.composio.dev/toolkits/parsio.md"
product: "platform"
version: null
last_updated: null
---

# Parsio

Parsio extracts structured data from emails, PDFs, and other documents using configurable parsers.

- **Category:** ai document extraction
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 10
- **Triggers:** 0
- **Slug:** `PARSIO`
- **Version:** 20260826_00

## Tools

### Get Document

**Slug:** `PARSIO_GET_DOCUMENT`

Get one Parsio document and its mailbox-specific parsed JSON fields.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `document_id` | string | Yes | Document ID returned by an ingestion or document-list tool. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Mailbox

**Slug:** `PARSIO_GET_MAILBOX`

Get settings and parser configuration for one Parsio mailbox.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `mailbox_id` | string | Yes | Mailbox ID returned by PARSIO_LIST_MAILBOXES. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Documents

**Slug:** `PARSIO_LIST_DOCUMENTS`

List and filter documents in a Parsio mailbox, one page at a time.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | Search by document name. |
| `cursor` | string | No | Opaque continuation cursor returned by a previous call. Omit for the first page; the cursor preserves the original mailbox, page size, and filters. |
| `status` | array | No | Return only documents in these processing states. Parsio's statuses are new, parsing, parsed, fail, skipped, quota, exception. |
| `to_date` | string | No | Include documents on or before this date in YYYY-MM-DD format. |
| `per_page` | integer | No | Maximum documents to return on this page (1-500). |
| `from_date` | string | No | Include documents on or after this date in YYYY-MM-DD format. |
| `mailbox_id` | string | Yes | Mailbox ID returned by PARSIO_LIST_MAILBOXES. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Mailboxes

**Slug:** `PARSIO_LIST_MAILBOXES`

List the Parsio mailboxes available to the connected account so their IDs can be used for parsing and configuration tasks.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Table Fields

**Slug:** `PARSIO_LIST_TABLE_FIELDS`

List the extraction fields configured for a Parsio mailbox.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `mailbox_id` | string | Yes | Mailbox ID returned by PARSIO_LIST_MAILBOXES. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Parse Text Document

**Slug:** `PARSIO_PARSE_TEXT_DOCUMENT`

Submit plain text or HTML to an existing template-based or GPT-powered Parsio mailbox, optionally waiting for the parsed result. This operation creates document data and consumes parsing credits.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `html` | string | No | HTML document content. When both html and text are supplied, Parsio uses html. |
| `name` | string | No | Document name or email subject. |
| `text` | string | No | Plain-text document content; required when html is omitted. |
| `metadata` | object | No | Custom JSON metadata returned with parsed output under __meta__. |
| `mailbox_id` | string | Yes | ID of a template-based or GPT-powered mailbox. |
| `sender_email` | string | No | Optional sender email address. |
| `recipient_email` | string | No | Optional recipient email address. |
| `wait_for_result` | boolean | No | If true, wait for parsed data; if false, return after Parsio accepts the document for asynchronous parsing. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Reparse Document

**Slug:** `PARSIO_REPARSE_DOCUMENT`

Queue an existing Parsio document to be parsed again. This operation consumes parsing capacity or credits and should not be retried blindly.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `document_id` | string | Yes | ID of the existing document to reprocess. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Skip Documents

**Slug:** `PARSIO_SKIP_DOCUMENTS`

Mark one or more documents in a Parsio mailbox as skipped. This changes their processing state and cannot be undone through this toolkit.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `mailbox_id` | string | Yes | Mailbox containing all specified documents. |
| `document_ids` | array | Yes | One or more document IDs to mark skipped. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Update Mailbox

**Slug:** `PARSIO_UPDATE_MAILBOX`

Update one or more settings on an existing Parsio mailbox. Provide at least one setting; omitted settings remain unchanged.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | New display name for the mailbox. |
| `mailbox_id` | string | Yes | Mailbox ID returned by PARSIO_LIST_MAILBOXES. |
| `email_prefix` | string | No | New inbound mailbox email prefix. |
| `alert_email_h` | integer | No | Interval in hours between mailbox email alerts, as reported by PARSIO_LIST_MAILBOXES. |
| `receive_email` | boolean | No | Whether this mailbox should accept inbound email. |
| `collect_emails` | boolean | No | Whether Parsio should collect email addresses found by this mailbox. |
| `process_attachments` | boolean | No | Whether Parsio should process attachments received by this mailbox. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Upload Document

**Slug:** `PARSIO_UPLOAD_DOCUMENT`

Upload one file to a Parsio mailbox for parsing, optionally waiting for the parsed result. This operation creates document data and consumes parsing credits.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | One supported file. Synchronous uploads are limited to 20 MB and cannot be ZIP; asynchronous uploads are limited to 50 MB and may be ZIP. |
| `metadata` | object | No | Custom JSON metadata returned with parsed output under __meta__; sent to Parsio as the multipart meta field. |
| `mailbox_id` | string | Yes | ID of the mailbox that should parse the file. |
| `wait_for_result` | boolean | No | If true, use synchronous parsing and return parsed data; if false, queue asynchronous parsing and return its document identifier. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |