What are the requirements to use ToolJet MCP Server?
Node.js v14 or higher, a ToolJet instance with admin access, and an MCP-compatible AI assistant.
@ToolJet
基本情報
Connect ToolJet to your AI assistants
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"tooljet": {
"command": "npx",
"args": [
"-y",
"@tooljet/mcp"
],
"env": {
"TOOLJET_ACCESS_TOKEN": "your-access-token",
"TOOLJET_HOST": "https://your-tooljet-instance.com"
}
}
}
}Get all users of a ToolJet instance
Get all workspaces of a ToolJet instance
Get all apps of a workspace in a ToolJet instance
Get a user in a ToolJet instance
create a user in a given workspace of ToolJet instance
update a user in a given workspace of ToolJet instance
update a user role in a given workspace of ToolJet instance
ToolJet MCP Server is a bridge that connects AI assistants (such as Claude, Cursor, and other MCP-compatible tools) to your ToolJet platform via the Model Context Protocol. It enables AI assistants to manage users and workspaces, access app information, and perform administrative tasks on a ToolJet instance programmatically.
Configure your MCP client (e.g., Claude, Cursor) with a JSON entry using npx -y @tooljet/mcp. Set the environment variables TOOLJET_ACCESS_TOKEN (from your ToolJet instance) and TOOLJET_HOST (your ToolJet instance URL). On Windows, prefix the command with cmd /c. Once configured, the AI assistant can call the provided tools.
Node.js v14 or higher, a ToolJet instance with admin access, and an MCP-compatible AI assistant.
You must obtain an access token from your ToolJet instance and set it as the `TOOLJET_ACCESS_TOKEN` environment variable. Refer to the ToolJet API documentation for enabling the API.
Prefix the `npx` command with `cmd /c` in the MCP client configuration JSON.
Tools for user management (`get-all-users`, `get-user`, `create-user`, `update-user`, `update-user-role`), workspace management (`get-all-workspaces`), and application management (`get-all-apps`).
Yes, the source code is available on GitHub at `https://github.com/ToolJet/tooljet-mcp`.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
A search tool helps dev to solve the naming things problem.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
不止于 CSS
コメント