mcp-server

ToolHive Studio: Manage MCP Servers

Name: ToolHive Studio: Manage MCP Servers
Author: stacklok

Founders get easy MCP server management with ToolHive Studio, for developers working with AI agents.

From the repo · “ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents”

171 stars26 forksTypeScriptGuide quality 8/10 · reviewed Jul 22Updated 10/23/2026100% free · open source

What it does

ToolHive Studio allows founders to easily install, manage, and run MCP servers and connect them to AI agents

When to use it

•You need to deploy multiple MCP servers for different AI agent environments
•You want to streamline the process of installing and managing MCP servers
•You need to connect MCP servers to AI agents for testing or production

Ready-to-paste prompt

Create a new MCP server instance with `node src/cli.js create-server --name my-server --port 25565`

Heads up: Ensure you have Node.js 16 or higher installed, as ToolHive Studio uses TypeScript and requires a compatible Node.js version

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/toolhive-studio && curl -fsSL https://workflowstacks.com/api/skills/toolhive-studio/claude-skill -o ~/.claude/skills/toolhive-studio/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ToolHive Studio: Manage MCP Servers works

Codeflow

Free to inspect

ToolHive Studio: Manage MCP Servers is a very large TypeScript project (~69k lines across 695 code files, plus 288 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~69k lines · 695 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Node.js

Needs API keys (.env)

TypeScript 99%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
package.json
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide
5
examples/registries/registry-with-groups.json
A worked example — copy this to get going

What's in each folder

docs/Documentation16 files

examples/Examples you can copy1 files

renderer/Folder646 files

main/Folder245 files

common/Folder29 files

utils/Helper scripts21 files

preload/Folder18 files

e2e-tests/Folder10 files

READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/toolhive-studio && curl -fsSL https://workflowstacks.com/api/skills/toolhive-studio/claude-skill -o ~/.claude/skills/toolhive-studio/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

stacklok

Language

TypeScript