mcpField
W
websitetoolbox-mcp

websitetoolbox-mcp

Local
github.com/webtoolboxSocial Media1Updated 17w ago

About websitetoolbox-mcp

websitetoolbox-mcp connects the Website Toolbox forum REST API to AI clients for forum administrators and operators. It covers community content and membership, including topics, posts, users, groups, and conversations.

Key features

  1. 01Manage categories, topics, and posts
  2. 02Manage users and user groups
  3. 03Manage conversations and messages
  4. 04Manage moderators, tags, and page views

Use cases

  1. 01Maintain forum topics and posts through an AI client
  2. 02Handle users, groups, and related permissions
  3. 03Look up messages, moderators, and page views

MCP support

The MCP server exposes Website Toolbox REST API forum resources and operations to MCP-compatible clients. It authenticates with a forum API key.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"websitetoolbox": {
"command": "npx",
"args": [
"-y",
"websitetoolbox-mcp"
]
}
}
}
Run commandnpx -y websitetoolbox-mcp

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
npmwebsitetoolbox-mcp1.0.0

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

Website Toolbox MCP

Chat with your forum using AI. The Website Toolbox MCP server lets you manage categories, topics, posts, users, and more through any MCP-compatible AI tool like Claude Desktop, Cursor, or Hermes Agent.

Install in Claude Desktop

  1. Open Claude Desktop. If you don't have it, download it first.
  2. Download the .mcpb bundle.
  3. In Claude Desktop, go to Settings (click your name at the bottom left, then the gear icon), then click Extensions in the left sidebar.
  4. Click Install from file and select the downloaded .mcpb file.
  5. When prompted, enter your forum's API key. You can find it in your forum's admin area under Integrate → API.
  6. Start a new conversation and ask something about your forum!

Features

ResourceTools
Categorieslist, get, create, update, delete, list permissions, update permissions
Topicslist, get, create, update, delete
Postslist, get, create, update, delete
Userslist, get, create, update, delete, follow topics, unfollow topics
User Groupslist, get, create, update, delete, add users, remove users
Conversationslist, get, create, delete
Messageslist, get, create
Moderatorslist, get, create, update, delete
Tagslist
Page Viewslist

For developers

Prerequisites
  • Node.js ≥ 18
Install
From npm
npm install -g websitetoolbox-mcp
From source
git clone https://github.com/webtoolbox/websitetoolbox-mcp
cd websitetoolbox-mcp
npm install
npm run build
Configure
  1. Get your API key from your forum's Integrate → API settings.

  2. Set it as an environment variable:

export WEBSITETOOLBOX_API_KEY="your-api-key"

On Windows:

set WEBSITETOOLBOX_API_KEY=your-api-key

Or create a .env file (copy .env.example to .env and fill in your key).

  1. Optional — act as a specific user:

    export WEBSITETOOLBOX_USERNAME="admin"
    export WEBSITETOOLBOX_EMAIL="[email protected]"
    
Claude Desktop (manual config)

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "websitetoolbox": {
      "command": "npx",
      "args": ["websitetoolbox-mcp"],
      "env": {
        "WEBSITETOOLBOX_API_KEY": "your-api-key"
      }
    }
  }
}
Other MCP clients

Run the server on stdio:

npx websitetoolbox-mcp
API Reference

This MCP server wraps the Website Toolbox REST API. See the full API documentation at https://www.websitetoolbox.com/docs/api/ or the API Documentation support article for details on authentication, endpoints, and rate limits.

License

MIT

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.