> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to Docsumo

The Docsumo connector lets your AI agent act in each user's Docsumo account. Each user connects their own Docsumo API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 30 tools.

**Authentication:** API Key
**Categories:** Files & Documents, AI
**Tools:** 30: 16 read, 10 write, 4 destructive
**Users sign in with:** API key
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=DOCSUMO)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Docsumo connection

   In **AgentKit > Connections**, create a Docsumo connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'docsumo'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Docsumo:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'docsumo_account_get',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "docsumo"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Docsumo:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="docsumo_account_get",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Docsumo credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'docsumo_account_get',
  toolInput: {},
  connector: 'docsumo',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="docsumo_account_get",
    tool_input={},
    connection_name="docsumo",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `docsumo_account_get`

Get Account And Document Types · Read-only

Get your Docsumo account details, monthly document usage and limits, and your active document types.
Returns email, full name, user ID, usage and limits, and document types with their doc_type values.
Use this to find doc_type values for docsumo_documents_list and folder creation.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `docsumo_agents_list`

List Agents · Read-only

List the agents (document types and case types) in your Docsumo account.
Returns agents with their IDs, names and kind.
Use this to find a casetype_id for the case tools.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `type` (`string`, optional): Which agents to list: all, doctype or casetype. Defaults to all. Example: casetype. One of: `all`, `doctype`, `casetype`.

Example input: `{}`

### `docsumo_bank_statement_analytics_get`

Get Bank Statement Analytics · Read-only

Get analytics for a processed bank statement: spending, cash flow and other financial patterns.
Returns the analytics as JSON (or a CSV or XLSX export when output is set).
Use mode all for the detailed report. Use docsumo_mca_analysis_run for merchant cash advance analysis across statements.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `doc_id` (`string`, required): doc_id of a processed bank statement. Example: 40269200cd7443178dea03f8cccea8d4.
- `mode` (`string`, optional): basic for a summary, all for the in-depth report. Defaults to basic. Example: basic. One of: `basic`, `all`.
- `output` (`string`, optional): Output format. Defaults to json. Example: json. One of: `json`, `csv`, `xlsx`.

Example input: `{"doc_id":"<doc_id>"}`

### `docsumo_case_get`

Get Case · Read-only

Get an overview of one case, optionally with its document types, fields, approvals, exports and documents.
Returns the case's name, stage, assignee, workflow state and the sections requested in include.
Use docsumo_cases_list to find case IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `case_id` (`string`, required): Case ID, from docsumo_cases_list. Example: case_73b2d9e1f4.
- `casetype_id` (`string`, required): Case type ID, from docsumo_agents_list. Example: ct_6a1f0c2e9b.
- `include` (`string`, optional): Comma-separated sections to include: doctypes, fields, approvals, exports, documents. Example: fields,documents.

Example input: `{"case_id":"<case_id>","casetype_id":"<casetype_id>"}`

### `docsumo_case_type_get`

Get Case Type · Read-only

Get the details of a case type: its stages, case fields and settings.
Returns the case type with stage IDs and field IDs.
Use this to find stage_id and case field IDs for docsumo_case_update and docsumo_cases_list.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `casetype_id` (`string`, required): Case type ID, from docsumo_agents_list. Example: ct_6a1f0c2e9b.

Example input: `{"casetype_id":"<casetype_id>"}`

### `docsumo_cases_list`

List Cases · Read-only

List the cases of a case type, filtered by stage, assignee, workflow state or dates, with pagination.
Returns cases with their IDs, names, stage, assignee, workflow state and timestamps.
Use this to find a case_id. Use docsumo_case_get for one case.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `casetype_id` (`string`, required): Case type ID, from docsumo_agents_list. Example: ct_6a1f0c2e9b.
- `assigned_to` (`array`, optional): Only cases assigned to these user IDs. Example: ["usr_51c2"]
- `created_date_from` (`string`, optional): Created on or after this date, DD/MM/YYYY. Example: 01/10/2026.
- `created_date_to` (`string`, optional): Created on or before this date, DD/MM/YYYY. Example: 31/10/2026.
- `limit` (`integer`, optional): Cases per page, 0 to 100. Defaults to 20. Example: 20.
- `modified_date_from` (`string`, optional): Modified on or after this date, DD/MM/YYYY. Example: 01/10/2026.
- `modified_date_to` (`string`, optional): Modified on or before this date, DD/MM/YYYY. Example: 31/10/2026.
- `offset` (`integer`, optional): Cases to skip, for pagination. Defaults to 0. Example: 0.
- `sort_by` (`string`, optional): Sort field and direction. Defaults to created_date.desc. Example: modified_date.desc. One of: `created_date.asc`, `created_date.desc`, `modified_date.asc`, `modified_date.desc`.
- `stage_id` (`array`, optional): Only cases in these stage IDs. Example: ["stg_review"]
- `workflow_state` (`array`, optional): Only cases in these workflow states. Example: ["completed"]

Example input: `{"casetype_id":"<casetype_id>"}`

### `docsumo_document_data_get`

Get Extracted Data · Read-only

Get the data extracted from a document in simplified JSON: key-value fields and tables, whether extracted by Docsumo or corrected by a user.
Returns the document's fields and table rows.
Use this once a document is processed. Use docsumo_document_field_update to correct a value.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `doc_id` (`string`, required): Docsumo document ID (doc_id), from docsumo_documents_list. Example: 40269200cd7443178dea03f8cccea8d4.

Example input: `{"doc_id":"<doc_id>"}`

### `docsumo_document_get`

Get Document · Read-only

Get the metadata of one document, including its pages and page image URLs.
Returns doc_id, title, type, status, pages with image URLs, and timestamps.
Use docsumo_document_data_get for the extracted field values.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `doc_id` (`string`, required): Docsumo document ID (doc_id), from docsumo_documents_list. Example: 40269200cd7443178dea03f8cccea8d4.

Example input: `{"doc_id":"<doc_id>"}`

### `docsumo_document_review_url_get`

Get Document Review URL · Read-only

Generate a temporary review URL for a document that people without a Docsumo account can open.
Returns the review URL, with a signed token when signed_url is true.
Use this to send a document for external review. Use docsumo_folder_review_url_get for a whole folder.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `doc_id` (`string`, required): Docsumo document ID (doc_id), from docsumo_documents_list. Example: 40269200cd7443178dea03f8cccea8d4.
- `signed_url` (`boolean`, optional): true to include a signed token so external users can open the link for a limited time. Example: true.

Example input: `{"doc_id":"<doc_id>"}`

### `docsumo_document_split_files_get`

Get Document Split Files · Read-only

Get the files of an auto-split document: the original file, the split files, or both, as presigned S3 URLs or base64.
Returns the requested files.
Use docsumo_document_split_info_get for the split metadata.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `original_doc_id` (`string`, required): doc_id of the original document before splitting. Example: 40269200cd7443178dea03f8cccea8d4.
- `file_format` (`string`, optional): Return files as s3_url, base64 or both. Defaults to s3_url. Example: s3_url. One of: `s3_url`, `base64`, `both`.
- `include_file` (`string`, optional): Which files to return. Defaults to original. Example: all. One of: `original`, `split`, `all`.

Example input: `{"original_doc_id":"<original_doc_id>"}`

### `docsumo_document_split_info_get`

Get Document Split Info · Read-only

Get how an auto-split document was divided: the original document and the documents split from it.
Returns split metadata, plus file URLs or base64 content when include_file is set.
Use docsumo_document_split_files_get when you only need the files.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `original_doc_id` (`string`, required): doc_id of the original document before splitting. Example: 40269200cd7443178dea03f8cccea8d4.
- `file_format` (`string`, optional): File format when include_file is set: s3_url, base64 or both. Defaults to s3_url. Example: s3_url. One of: `s3_url`, `base64`, `both`.
- `include_file` (`string`, optional): Which files to include: original, split or all. Without it only metadata is returned. Example: split. One of: `original`, `split`, `all`.

Example input: `{"original_doc_id":"<original_doc_id>"}`

### `docsumo_document_types_list`

List Enabled Document Types · Read-only

List the document types enabled for your Docsumo account.
Returns the enabled document types.
Use docsumo_account_get for usage limits alongside the types.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `docsumo_documents_list`

List Documents · Read-only

List the documents in your Docsumo account, filtered by folder, type, status, title search or creation date, with pagination.
Returns documents with doc_id, title, type, status, folder and timestamps.
Use this to find a doc_id. Use docsumo_document_get for one document's details and docsumo_document_data_get for its extracted data.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `created_date` (`string`, optional): Creation date filter as operator:YYYY-MM-DD, with gte or lte. Example: gte:2025-03-20.
- `doc_type` (`string`, optional): Only this document type, a doc_type value from docsumo_account_get. Example: invoice.
- `folder_id` (`string`, optional): Folder to list. Required when view is folder. Example: cbbe31d3b37a4c2a95518dd7edf4c24e.
- `limit` (`integer`, optional): Documents to return, up to 20. Example: 20.
- `offset` (`integer`, optional): Documents to skip, for pagination. Example: 0.
- `q` (`string`, optional): Partial-match search on document titles. Example: acme.
- `sort_by` (`string`, optional): Sort by creation date. Example: created_date.desc. One of: `created_date.asc`, `created_date.desc`.
- `status` (`string`, optional): Only documents with this processing status. Example: processed. One of: `reviewing`, `processed`, `erred`.
- `view` (`string`, optional): files for documents outside folders, folder for documents in folder_id, all_files for everything. Example: all_files. One of: `files`, `folder`, `all_files`.

Example input: `{}`

### `docsumo_documents_summary_get`

Get Documents Summary · Read-only

Get a summary of your documents grouped by document type, with counts per processing status.
Returns, per document type, the number of documents in each status.
Use this for a quick overview. Use docsumo_documents_list to list documents.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `docsumo_folder_review_url_get`

Get Folder Review URL · Read-only

Generate a shareable review link for a folder of documents that people without a Docsumo account can open.
Returns the review URL.
Use docsumo_document_review_url_get for a single document.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `folder_id` (`string`, required): Folder ID. Example: baf65ce1b85c43eca37cdfadb0a621d2.

Example input: `{"folder_id":"<folder_id>"}`

### `docsumo_table_data_get`

Get Database Table Data · Read-only

Get all rows of a Docsumo database table (used for validation and mapping).
Returns the table's headers and rows with their row IDs.
Use row IDs and headers with docsumo_table_cell_update.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `ddid` (`string`, required): Database table ID. Example: 6650f1a2b3c4d5e6f7a8b9c0.

Example input: `{"ddid":"<ddid>"}`

### `docsumo_case_share_token_create`

Create Case Share Token · Write

Create a short-lived token for a read-only shareable or embeddable view of one case.
Returns the temporary token.
Use this to show a case to someone outside Docsumo.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `case_id` (`string`, required): Case ID, from docsumo_cases_list. Example: case_73b2d9e1f4.

Example input: `{"case_id":"<case_id>"}`

### `docsumo_case_update`

Update Case · Write

Update a case: move it to a stage, change case fields, reassign it, rename it, or approve or reject a pending review, and optionally run its workflow afterwards.
Returns the updated case.
Get stage and field IDs from docsumo_case_type_get.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `case_id` (`string`, required): Case ID, from docsumo_cases_list. Example: case_73b2d9e1f4.
- `casetype_id` (`string`, required): Case type ID, from docsumo_agents_list. Example: ct_6a1f0c2e9b.
- `approval` (`object`, optional): Human-in-the-loop decision for a pending review: id (approval block ID), is_approved (true approves, false rejects) and an optional reason. Example: {"id": "apr_19d", "is_approved": true, "reason": "Verified"}
- `assigned_to` (`string`, optional): User ID of the new assignee. Example: usr_51c2.
- `case_fields` (`object`, optional): Case field values to set, keyed by field ID. Example: {"cf_amount": "1250.00"}
- `case_name` (`string`, optional): New name for the case. Example: Acme loan application.
- `stage_id` (`string`, optional): Stage to move the case to. Example: stg_approved.
- `trigger_workflow` (`boolean`, optional): true to run the case type's workflow after the update. Defaults to false. Example: false.

Example input: `{"case_id":"<case_id>","casetype_id":"<casetype_id>"}`

### `docsumo_case_workflow_run`

Run Case Workflow · Write

Run the workflow of a case type on one case.
Returns the workflow run result.
Use docsumo_case_update with trigger_workflow true to update and run in one call.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `case_id` (`string`, required): Case ID, from docsumo_cases_list. Example: case_73b2d9e1f4.
- `casetype_id` (`string`, required): Case type ID, from docsumo_agents_list. Example: ct_6a1f0c2e9b.

Example input: `{"case_id":"<case_id>","casetype_id":"<casetype_id>"}`

### `docsumo_document_field_update`

Update Extracted Field · Write

Correct the value of one extracted field in a document.
Returns the updated field.
Get field IDs from docsumo_document_data_get.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `doc_id` (`string`, required): Docsumo document ID (doc_id), from docsumo_documents_list. Example: 40269200cd7443178dea03f8cccea8d4.
- `field_id` (`string`, required): ID of the field to update, from docsumo_document_data_get. Example: 1001.
- `value` (`string`, required): New value for the field. Example: INV-2026-0042.

Example input: `{"doc_id":"<doc_id>","field_id":"<field_id>","value":"<value>"}`

### `docsumo_document_review_status_update`

Update Document Review Status · Write

Start a review of a document, mark its review complete, or skip review.
Returns the updated review status.
Use end to approve a document after checking docsumo_document_data_get.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `action` (`string`, required): Review action: start, end (complete) or skip. Example: end. One of: `start`, `end`, `skip`.
- `doc_id` (`string`, required): Docsumo document ID (doc_id), from docsumo_documents_list. Example: 40269200cd7443178dea03f8cccea8d4.
- `forced` (`boolean`, optional): true to change the status even if the document has validation errors. Example: false.
- `strict` (`boolean`, optional): For end only: true to fail if any data field has a validation error. Example: true.

Example input: `{"action":"start","doc_id":"<doc_id>"}`

### `docsumo_documents_move`

Move Documents · Write

Move one or more documents from one folder to another.
Returns the move result.
Get folder IDs from docsumo_documents_list (folder view) or docsumo_folder_create.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `dest_folder_id` (`string`, required): Folder to move the documents to. Example: baf65ce1b85c43eca37cdfadb0a621d2.
- `doc_ids` (`array`, required): doc_ids of the documents to move. Example: ["40269200cd7443178dea03f8cccea8d4"]
- `source_folder_id` (`string`, required): Folder the documents are in now. Example: cbbe31d3b37a4c2a95518dd7edf4c24e.

Example input: `{"dest_folder_id":"<dest_folder_id>","doc_ids":["40269200cd7443178dea03f8cccea8d4"],"source_folder_id":"<source_folder_id>"}`

### `docsumo_folder_create`

Create Folder · Write

Create a folder for organizing documents of one document type.
Returns the created folder with its folder_id.
Use docsumo_documents_move to put documents in it.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `folder_name` (`string`, required): Name of the new folder. Example: Q4 invoices.
- `type` (`string`, required): Document type the folder holds, a doc_type value from docsumo_account_get. Example: invoice.

Example input: `{"folder_name":"<folder_name>","type":"<type>"}`

### `docsumo_mca_analysis_run`

Run MCA Analysis · Write

Run a merchant cash advance (MCA) account-summary analysis across one or more processed bank statements.
Returns the account summary analysis.
Use docsumo_bank_statement_analytics_get for a single statement's analytics.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `doc_ids` (`array`, required): doc_ids of the bank statements to analyze. Example: ["40269200cd7443178dea03f8cccea8d4"]
- `allow_partial` (`boolean`, optional): true to process even if some documents are not in a valid status. Defaults to false. Example: false.
- `mca_list_db_table` (`string`, optional): Database table name holding the MCA lender list. Example: mca_lenders.
- `non_mca_list_db_table` (`string`, optional): Database table name holding the non-MCA list. Example: non_mca_lenders.
- `webhook` (`boolean`, optional): true to send a webhook notification when processing finishes. Defaults to false. Example: false.

Example input: `{"doc_ids":["40269200cd7443178dea03f8cccea8d4"]}`

### `docsumo_table_cell_update`

Update Database Table Cell · Write

Set the value of one cell in a database table, identified by row ID and column header.
Returns the update result.
Get row IDs and headers from docsumo_table_data_get.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `ddid` (`string`, required): Database table ID. Example: 6650f1a2b3c4d5e6f7a8b9c0.
- `header` (`string`, required): Column header name. Example: CustomerName.
- `id` (`integer`, required): Row ID. Example: 1001001.
- `value` (`string`, required): New cell value. Example: Acme Corp.

Example input: `{"ddid":"<ddid>","header":"<header>","id":1001001,"value":"<value>"}`

### `docsumo_table_row_add`

Add Database Table Row · Write

Add an empty row at the end of a database table. It gets the next sequential ID and empty values.
Returns the new row.
Fill it with docsumo_table_cell_update.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `ddid` (`string`, required): Database table ID. Example: 6650f1a2b3c4d5e6f7a8b9c0.

Example input: `{"ddid":"<ddid>"}`

### `docsumo_cases_delete`

Delete Cases · Destructive

Permanently delete up to 100 cases of a case type.
Returns the deletion result.
Get case IDs from docsumo_cases_list.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `case_ids` (`array`, required): 1 to 100 case IDs to delete. Example: ["case_73b2d9e1f4"]
- `casetype_id` (`string`, required): Case type ID, from docsumo_agents_list. Example: ct_6a1f0c2e9b.

Example input: `{"case_ids":["case_73b2d9e1f4"],"casetype_id":"<casetype_id>"}`

### `docsumo_document_delete`

Delete Document · Destructive

Permanently delete a document.
Returns a confirmation.
Get the doc_id from docsumo_documents_list.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `doc_id` (`string`, required): Docsumo document ID (doc_id), from docsumo_documents_list. Example: 40269200cd7443178dea03f8cccea8d4.

Example input: `{"doc_id":"<doc_id>"}`

### `docsumo_entity_records_delete`

Delete Entity Records · Destructive

Permanently delete up to 1,000 records of an entity, by record ID or by primary key value, with their files, comments and links.
Returns the deletion result.
Send record_ids or primary_key_values.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `entity_id` (`string`, required): Entity ID, from the entity's URL in Docsumo: /tables/<entity_id>. Example: ent_2c9a71.
- `primary_key_values` (`array`, optional): Primary key column values of the records to delete. The entity must have a primary key column. Example: ["INV-1001"]
- `record_ids` (`array`, optional): IDs of the records to delete, from the record URL /tables/<entity_id>/record/<record_id>. Example: ["rec_8f31"]

Example input: `{"entity_id":"<entity_id>"}`

### `docsumo_tables_delete`

Delete Database Tables · Destructive

Permanently delete one or more database tables.
Returns the deletion result.
This cannot be undone.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `dd_ids` (`array`, required): IDs of the tables to delete. Example: ["6650f1a2b3c4d5e6f7a8b9c0"]

Example input: `{"dd_ids":["6650f1a2b3c4d5e6f7a8b9c0"]}`

## Related

Other Files & Documents connectors ([all 76](/agentkit/connectors/?category=files-documents)):

- [Notion](/agentkit/connectors/notion/): Scalekit connector, OAuth, 51 tools
- [Google Sheets](/agentkit/connectors/googlesheets/): Scalekit connector, OAuth, 48 tools
- [Google Drive](/agentkit/connectors/googledrive/): Scalekit connector, OAuth, 47 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
