Lets you install, run, and manage MCP servers in secure containers and connect them to AI clients like Cursor and Claude Code.
Also known as stacklok/toolhive-studio
- Stars
- 172
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- Apache-2.0
What is ToolHive MCP?
ToolHive lets you install, run, and manage MCP servers in secure containers and connect them to AI clients like Cursor and Claude Code.
Summary generated from the project's README
About ToolHive MCP server
Deploying and managing Model Context Protocol servers through a graphical interface is what ToolHive Studio enables for developers. It provides a desktop application that runs on Windows, macOS, or Linux to help users discover and launch MCP servers inside isolated, locked-down containers. This approach ensures that each server operates with only the necessary permissions and keeps secrets secure rather than storing them in plaintext.
Users can connect these containerized servers to popular AI clients such as Cursor, Claude Code, and GitHub Copilot via an HTTP/SSE proxy. While the desktop UI offers a simple workflow for most tasks, the system also includes a command-line tool for standalone use and a Kubernetes Operator for more advanced environments. This setup removes the need for manual configuration or complex runtime management when integrating new tools into your AI development workflow.
What you can do with it
- 1Securely launch MCP serversYou can start any MCP server within a protected container using a simple graphical workflow.
- 2Connect tools to AI clientsIntegrate your managed servers directly into coding assistants like Cursor or Claude Code.
- 3Manage servers via command lineAdvanced users can interact with the system using a CLI instead of the desktop interface.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablestacklok/toolhive-studio is public and reachablegithub.com/stacklok/toolhive-studio ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/stacklok/toolhive-studio ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub
ToolHive desktop UI
Run any Model Context Protocol (MCP) server — securely, instantly, anywhere.
ToolHive is the easiest way to discover, deploy, and manage MCP servers. Launch any MCP server in a locked-down container with just a few clicks. No manual setup, no security headaches, no runtime hassles.
Quick links
- 🚀 Quickstart - install ToolHive and run your first MCP server
- 📚 Documentation - learn more about ToolHive's features
- 💬 Discord community - connect with the ToolHive community, ask questions, and share your experiences
- 🛠️ Developer guide - build, test, and contribute to the ToolHive UI
Why ToolHive?
- Instant deployment: Start any MCP server with a simple graphical workflow.
- Secure by default: Every server runs in an isolated container with only the permissions it needs. Secrets are managed securely, never in plaintext.
- Works everywhere: Runs on Windows, macOS, or Linux.
- Seamless integration: ToolHive auto-configures popular clients like GitHub Copilot, Cursor, Claude Code, and more.
Getting started
To get started with ToolHive, download the latest release from the website and follow the quickstart guide.
How it works
Under the hood, ToolHive runs each MCP server in its own secure container and exposes an HTTP/SSE proxy that MCP clients connect to.
For more advanced use cases, ToolHive is also available as a command-line tool which can be used standalone or side-by-side with the ToolHive UI and as a Kubernetes Operator. Learn more in the ToolHive documentation.
Privacy and telemetry
ToolHive uses Sentry for error tracking and performance monitoring to help us identify and fix issues, improve stability, and enhance the user experience. This telemetry is enabled by default but completely optional.
What data is collected?
- Error reports and crash logs
- Performance metrics
- Usage patterns
How to opt out
You can easily disable telemetry at any time:
- Open ToolHive
- Go to Settings (gear icon in the top navigation)
- Find the Telemetry section
- Toggle off telemetry collection
Contributing
We welcome contributions and feedback from the community!
If you have ideas, suggestions, or want to get involved, check out our contributing guide or open an issue. Join us in making ToolHive even better!
License
This project is licensed under the Apache 2.0 License.
ToolHive MCP questions
How does ToolHive run MCP servers securely?
It launches every MCP server in an isolated container with only the permissions it needs, and secrets are managed securely rather than in plaintext.
What platforms does the ToolHive desktop UI support?
ToolHive runs on Windows, macOS, and Linux.
Which AI clients can ToolHive configure?
It auto-configures popular clients such as GitHub Copilot, Cursor, and Claude Code.
How do I turn off ToolHive telemetry?
Open Settings via the gear icon, find the Telemetry section, and toggle off telemetry collection.
Is there a command-line version of ToolHive?
Yes, ToolHive is also available as a CLI that can be used standalone or alongside the UI, plus a Kubernetes Operator.