UNDATASIO_MCP

Created By

Alex2 months ago

Unlock flawless, AI-ready data with guaranteed ROI. undatasio's new engine offers unrivaled accuracy and speed, all on a secure platform. Our revolutionary model means you only pay for results.

# undatasio

# data-processing

Overview Content Tools Comments

Content

API Documentation - UnDatas.io Service

This document provides details for the API service built around the UnDatas.io third-party library.

1. List Workspaces

Summary: Retrieves a list of all workspaces available to the user.
Endpoint: GET /api/v1/undatas/workspaces
Parameters: None
Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON array containing workspace objects.

2. List Tasks in a Workspace

Summary: Fetches all tasks within a specific workspace, identified by its ID.
Endpoint: GET /api/v1/undatas/workspaces/{work_id}/tasks
Parameters:

Parameter	Location	Required	Description
`work_id`	Path	Yes	The unique identifier for the target workspace.

Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON array containing task objects.

3. Get Files in a Task

Summary: Retrieves a list of all files uploaded to a specific task, identified by its ID.
Endpoint: GET /api/v1/undatas/tasks/{task_id}/files
Parameters:

Parameter	Location	Required	Description
`task_id`	Path	Yes	The unique identifier for the target task.

Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON array containing file objects.

4. Upload a File to a Task

Summary: Uploads a single file to a specified task.
Endpoint: POST /api/v1/undatas/tasks/{task_id}/upload
Parameters:

Parameter	Location	Required	Description
`task_id`	Path	Yes	The unique identifier for the target task.
`file`	Form Data	Yes	The file to be uploaded.

Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON object with a success message, e.g., {"message": "File uploaded successfully"}.

5. Parse Files in a Task

Summary: Initiates the parsing process for one or more files within a specified task.
Endpoint: POST /api/v1/undatas/tasks/parse
Request Body: application/json

Field	Type	Required	Description
`task_id`	string	Yes	The unique identifier for the target task.
`file_ids`	array[string]	Yes	A list of file IDs to be parsed.
`ds_id`	string	No	The data source ID. Defaults to `"default"`.
`lang`	string	No	The language for parsing. Defaults to `"ch"`.
`parse_mode`	string	No	The parsing mode. Defaults to `"fast"`.

Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON object with a success message, e.g., {"message": "File parsing initiated successfully."}.

6. Get Parse Result for a File

Summary: Retrieves the detailed parsing results for a single, specific file.
Endpoint: POST /api/v1/undatas/tasks/parse-result
Request Body: application/json

Field	Type	Required	Description
`task_id`	string	Yes	The ID of the task containing the file.
`file_id`	string	Yes	The ID of the file to retrieve results for.

Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON object containing the file's parsing result data.

7. Get Download URL for Parsed Results

Summary: Generates and returns a download URL for the parsed results of one or more files.
Endpoint: POST /api/v1/undatas/tasks/download-url
Request Body: application/json

Field	Type	Required	Description
`task_id`	string	Yes	The ID of the task containing the files.
`file_ids`	array[string]	Yes	A list of file IDs to include in the download.

Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON object containing the download URL, e.g., {"download_url": "https://..."}.

8. Health Check

Summary: Checks if the API service is running and healthy.
Endpoint: GET /
Parameters: None
Successful Response:
- Code: 200 OK
- Content-Type: application/json
- Body: A JSON object indicating the service status, e.g., {"status": "ok"}.

Server Config

{
  "mcpServers": {
    "undatasio_mcp": {
      "autoApprove": [],
      "disabled": false,
      "timeout": 60,
      "type": "sse",
      "url": "http://3.145.49.189:8000/mcp"
    }
  }
}

Recommend Clients

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

WindsurfThe new purpose-built IDE to harness magic

chatmcpChatMCP is an AI chat client implementing the Model Context Protocol (MCP).

ChatWiseThe second fastest AI chatbot™

Roo Code (prev. Roo Cline)Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.

CursorThe AI Code Editor

Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code

y-cli 🚀A Tiny Terminal Chat App for AI Models with MCP Client Support

Cline – #1 on OpenRouterAutonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.

ZedCode at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

DeepChatYour AI Partner on Desktop