What is tooljet-mcp AGENTS.md?

Repository instructions for ToolJet's MCP tool layer. MCP is a standard way for an agent to call external tools; here, the built server calls ToolJet's REST API so an agent can change a ToolJet app directly.

Use it when building, testing, or running the ToolJet MCP server, its plugin bundle, its agent skill, or its connections to ToolJet and the gateway.

It explains how the repository fits into the larger system and prevents agents from relying on incorrect setup, build, or runtime assumptions.

How ToolJet/tooljet-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ToolJet/tooljet-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ToolJet/tooljet-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ToolJet/tooljet-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tooljet/tooljet-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/tooljet/tooljet-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/tooljet/tooljet-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tooljet/tooljet-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tooljet/tooljet-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/tooljet/tooljet-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,306 This file is loaded in full into every session.

When invoked 1,306 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01306	$0.01306
Opus 5.5	$0.00522	$0.00522
Sonnet 5.5	$0.00261	$0.00261
Haiku 4.5	$0.00131	$0.00131

Measured 6d ago against content hash 2a1546c104cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tooljet-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tooljet-mcp — AGENTS.md

Boundaries and traps only. Values and mechanics live in the code; when this file and the code disagree, trust the code. Local whole-stack setup: ToolJet/tooljet-agent, ai-stack/SETUP.md.

1. Purpose

The tool layer. npm run build:plugin produces bundle/index.js, a modular stdio MCP server with readable dependency chunks that tooljet-agent spawns per build; its tools call ToolJet's REST API with the PAT or session token the agent passes, so an agent changes a ToolJet app directly instead of emitting a spec. It also ships skills/tooljet-app-builder/, the skill (system prompt) the agent loads. The repo is also its own Claude Code / Codex plugin marketplace (.claude-plugin/, .codex-plugin/, mcp.json runs the prebuilt bundle).

2. Place in the stack

tooljet-agent ──stdio spawn──► tooljet-mcp bundle/index.js ──REST──► ToolJet
Claude Code / Codex ──stdio (plugin)──► tooljet-mcp bundle/index.js ──REST──► ToolJet
ToolJet AI shim ──HTTP, gateway mode──► tooljet-mcp ──REST──► ToolJet
tooljet-mcp ──POST /internal/mcp/verify-origin──► ai-api-gateway   (only if MCP_GATEWAY_URL set)

3. How it works

Writes land as a person. A PAT is exchanged for a ToolJet session (pinned to the workspace it was issued in); an in-product sessionToken needs a workspaceId and is short-lived, so a 401 mid-build means the build outlived it. Never add a system identity (src/auth.ts, src/config.ts RequestIdentity).
Transports (src/index.ts): stdio (what the agent uses); MCP_TRANSPORT=http without MCP_SHARED_TOKEN = direct mode, PAT per request, loopback; with it = gateway mode, bearer gate, binds 0.0.0.0, user named by x-tooljet-session + x-tooljet-workspace-id. npm run dev:http (src/http.ts) is a separate standalone server with no bearer gate.
identityFromHeaders (src/config.ts) throws on session-without-workspace, workspace-without-session and PAT+session together: failing beats mis-attributing a build.
Origin verification: x-tooljet-url must pass validateApiUrl and be in MCP_ALLOWED_API_ORIGINS or be verified by the gateway for x-tooljet-customer-id (checkOriginWithGateway). The gateway check fails closed and caches verdicts, so a revoked customer stays allowed until the cache TTL expires (GATEWAY_CACHE_TTL_MS).
Tools: src/tools/index.ts registerTools. Singular create tools are hidden unless TOOLJET_INCLUDE_LEGACY_SINGULAR_TOOLS=1; agents get the batch versions.

Read the full file on GitHub · 77 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago Changed · +3 tokens per session 2a1546c104cd
15d ago Changed · +1 lines · +17 tokens per session c35639d55933
1mo ago First seen · 76 lines · 1,286 tokens per session scan A 475bf641c98a

Subscribe to this mod's changes

tooljet-mcp AGENTS.md is an instructions file published in the GitHub repository ToolJet/tooljet-mcp (31 stars, last pushed today), licensed MIT. It adds 1,306 tokens to every session, about $0.0052 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.

Backend and APIs Building agents

tooljet-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tooljet-mcp AGENTS.mdToolJet/tooljet-mcp	Instructions file	31	today	MIT	A	1,306	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

tooljet-mcp: Instructions file for Codex