Skip to main content

Overview

BETA

ToolJet MCP is currently in beta and not recommended for production use.

The Model Context Protocol (MCP) is a standard for connecting Large Language Models (LLMs) to platforms like ToolJet. This guide covers how to connect ToolJet to AI tools using MCP, enabling your AI assistants to interact with and manage your ToolJet instance.

What is ToolJet MCP?​

ToolJet MCP is a bridge that connects AI assistants to your ToolJet platform through the Model Context Protocol. This allows AI tools to:

Create Applications

Build new apps from a prompt, with pages, queries, and components generated for you.

Modify Applications

Update existing apps by adding components, editing queries, or restructuring pages.

User Management

Create users, update their profiles, and manage roles across your workspaces.

Interact in Natural Language

Query and manage your ToolJet instance by describing what you need in plain language.

Supported LLMs​

ToolJet MCP works with the following LLM providers:

Claude Code
Anthropic's coding agent in the terminal
Codex
OpenAI's coding agent in the CLI or IDE
Grok Build
xAI's agentic building experience
Others
Any MCP-compatible client, such as Cursor or Cline
Data Access

An agent connected over MCP acts with the permissions of your access token and can run read queries against the data sources in that workspace. Because an agent's exploration is not deterministic and depends on the model you use, assume that any data reachable from that workspace may be read while it works. Scope the token to a workspace you are comfortable exposing.

Token Usage

The number of tokens consumed by an operation depends on the model you select, its reasoning effort setting, and the complexity of the request. These tokens are billed by your AI client's model provider, not by ToolJet.

Benefits of Using ToolJet MCP​

  • No ToolJet credits: Operations run on your AI client's own model subscription, so building through MCP doesn't draw down your ToolJet AI credits.
  • Better output: Agents build against ToolJet's governed first-party contracts, so they work from the platform's real schemas instead of guessing at its internals.
  • Stays in your workflow: Create and modify apps from the editor you already work in, with no context switching into ToolJet.
  • Browser-tested: Agents with browser access can open the app they built and verify it actually works before handing it back.
  • Extensible: Pair ToolJet MCP with other skills, tools, and MCP servers to extend what your agent can do.