What is toolhive-studio AGENTS.md?

General coding guidance for ToolHive Studio, an Electron desktop app for managing MCP servers. It covers the required Node.js version, commands, project boundaries, common setup problems, and code conventions.

Use it when setting up the project, starting development, checking types, linting, formatting, running tests, regenerating the API client, or investigating issues such as a stopped Docker daemon.

It gives AI coding assistants the context and checks needed to make compatible changes and avoid failures caused by missing services or the wrong runtime version.

toolhive-studio AGENTS.md — Instructions file by stacklok

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/stacklok/toolhive-studio/agents-md

Clone the repo

git clone --depth 1 https://github.com/stacklok/toolhive-studio

Made for: Codex, OpenCode.

Per session 603 This file is loaded in full into every session.

When invoked 603 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00603	$0.00603
Opus 5	$0.00302	$0.00302
Sonnet 5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured yesterday against content hash 7b948ba3b5aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toolhive-studio 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 yesterday.

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 · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This file provides guidance to AI coding assistants working with this repository.

Project Overview

ToolHive Studio is an Electron desktop application for managing MCP (Model Context Protocol) servers. Built with React, TypeScript, Electron, and Vite. Uses pnpm as package manager. Requires Node.js >=24 <25.

Essential Commands

pnpm install                    # Install dependencies
pnpm run start                  # Start dev server with hot reload
pnpm run lint                   # Run ESLint
pnpm run type-check             # TypeScript type checking
pnpm run format                 # Format with Prettier
pnpm run test:nonInteractive    # Run unit tests once
pnpm run test:coverage          # Unit tests with coverage
pnpm run e2e                    # End-to-end tests
pnpm run generate-client        # Regenerate API client from OpenAPI spec
pnpm run knip                   # Detect unused code

Husky/lint-staged automatically run lint + format on staged files. Run pnpm run type-check manually before committing.

Common Gotchas

Docker daemon must be running before pnpm run start
Node.js version must be >=24 <25 — some native modules break on wrong Node version
If API type errors appear, run pnpm run generate-client to refresh
Tests run through Electron (pnpm run vitest:electron), not plain Node
Always run commands from the repository root, not from subdirectories

Boundaries

Do not modify or manually edit:

common/api/generated/* — regenerate via pnpm run generate-client
renderer/src/route-tree.gen.ts — auto-generated by TanStack Router plugin
node_modules/, out/, .vite/ — build artifacts

Code Conventions

File names: kebab-case always (e.g., card-mcp-server.tsx)
Components: PascalCase, functional with hooks
Path aliases: @/* (renderer/src), @common/*, @utils/*, @mocks/*
Imports: use aliases for cross-directory imports, not relative paths
Exports: named exports preferred over default exports

Read the full file on GitHub · 62 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.

yesterday First seen · 62 lines · 603 tokens per session scan A 7b948ba3b5aa

Subscribe to this mod's changes

toolhive-studio AGENTS.md is an instructions file published in the GitHub repository stacklok/toolhive-studio (163 stars, last pushed 3d ago), licensed Apache-2.0. It adds 603 tokens to every session, about $0.0030 per session on Opus 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 2026-08-30.

Backend and APIs Security Testing ai ai-security developer-tools mcp mcp-client mcp-server

toolhive-studio AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Project Overview

Essential Commands

Common Gotchas

Boundaries

Code Conventions

What this file has done since we first saw it

Other instructions, from other repositories

stride-gpt AGENTS.md

Embody AGENTS.md

.context copilot-instructions.md

assay CLAUDE.md

examples CLAUDE.md

tengu CLAUDE.md