mcpField
S
Skywork Super Agents

Skywork Super Agents

Local
github.com/Skywork-aiProductivity55Updated 75w ago

About Skywork Super Agents

Skywork Super Agents is a lightweight MCP server offering office tools that generate PPTs, documents, spreadsheets, webpages and broadcasts. It suits users who want an AI client to produce office files, with the output returned as a URL.

Key features

  1. 01Generates PPTs, documents, spreadsheets, webpages and broadcasts
  2. 02Dependency setup and launch with uv
  3. 03API key authentication through SKYWORK_API_KEY

Use cases

  1. 01Generating a slide deck or report document from a description
  2. 02Producing spreadsheets or webpage content quickly

MCP support

This project is an MCP server launched via the office-tool command that provides office file generation tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"Skywork-Super-Agents": {
"command": "uvx",
"args": [
"office-tool"
],
"env": {
"SKYWORK_API_KEY": "<SKYWORK_API_KEY>"
}
}
}
}
Run commanduvx office-tool
Environment variables to set
SKYWORK_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypioffice-tool

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Skywork-Super-Agents

A lightweight MCP server offering office tools to generate various file types, including PPTs, documents, spreadsheets, webpages and broadcasts.

Setup

  1. Install dependencies using uv:
uv venv
uv sync
  1. Create a .env file with your SkyWork API key:
SKYWORK_API_KEY=your_api_key_here

"You can request an API key by reaching out to [email protected]."

Running the Server

{
    "mcpServers": {
        "office": {
            "command": "uvx",
            "args": ["--from", "git+https://github.com/Skywork-ai/Skywork-Super-Agents.git", "office-tool"],
            "env": {
                "SKYWORK_API_KEY": "your_api_key_here"
            }
        }
    }
}

API Usage Response

Response:

{
    "url": "output_oss_url"
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.