SuperAPI AI Directory
Partner with us中文AI newsFavorites
All toolsAI developer platformstoolhive

toolhive

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers. Developed and open-sourced by Stacklok, it uses a modular architecture comprising three main components: Gateway, Registry Server, and Runtime, and supports operation through a desktop UI or command-line interface (CLI). ToolHive runs each MCP server in an isolated container, and once authentication sources are configured, it can enforce identity and access policies per request and provide observability, helping platform teams put MCP into production. It supports local Docker or Podman operation and can also be deployed in clusters through the Kubernetes Operator, making it suitable for individual developers, teams, and enterprise organizations.

Open website

About this tool

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers, developed by Stacklok and open-sourced under the Apache 2.0 license.

Purpose

ToolHive is designed to help developers, teams, and enterprises securely run, manage, and integrate MCP servers. It can run any MCP server in an isolated container, and once authentication sources are configured, it enforces identity and access policies per request while providing the observability required for production environments.

Main Capabilities

  • Secure Operation: Each MCP server runs in an isolated container, and once authentication sources are configured, identity and access policies can be enforced per request.
  • Modular Architecture: Composed of Gateway, Registry Server, and Runtime, accessible through the ToolHive UI and CLI.
  • Gateway: Defines dedicated endpoints for teams to access tools securely and efficiently; can orchestrate multiple tools into a virtual MCP with a deterministic workflow engine; defines access policies and network endpoints; centrally controls security policies, authentication, authorization, auditing, and more; integrates with IdPs for SSO (compatible with OIDC/OAuth); customizes and filters tools and descriptions to improve performance and reduce token usage; connects local clients such as Claude Desktop, Cursor, VS Code, and VS Code Server.
  • Registry Server: Curates a catalog of trusted servers for teams to quickly discover and deploy; integrates with the official MCP registry; adds custom MCP servers; groups servers by role or use case; manages the registry through an API-driven interface; verifies provenance and signs servers through built-in security controls; provides preset configurations and permissions.
  • Runtime: Deploys, runs, and manages MCP servers locally or in Kubernetes clusters, with security protections; deploys in the cloud through Kubernetes for enterprise-grade scale; runs locally through Docker or Podman; securely proxies remote MCP servers; provides a Kubernetes Operator for cluster and resource management; uses OpenTelemetry and Prometheus for monitoring and audit logging.
  • Flexible Interfaces: Use ToolHivGet a cross-platform desktop experience with the UI, or use the ToolHive CLI for terminal workflows and automation; discover, configure, and run MCP servers; automatically connect managed MCP servers to compatible AI clients.

How to Use

ToolHive offers three quick-start paths: a desktop application, a CLI, and a Kubernetes Operator. Individual developers can get started within minutes via the desktop UI or CLI, and run any MCP server from a container image, or dynamically build from common package managers; they can manage encryption keys and control network isolation through simple local tools; they can test and validate MCP servers using built-in tools (such as the official MCP Inspector); and they can optimize token usage and tool execution using MCP Optimizer. Teams and organizations can centrally manage MCP servers and registries using familiar Kubernetes workflows.

Use Cases

  • Individual developers running and managing MCP servers on their local machines.
  • Teams and organizations centrally managing MCP servers and registries in Kubernetes clusters.
  • Enterprise teams integrating MCP servers into custom internal tools, agent workflows, or chat-based interfaces.
  • Running MCP servers on developer machines, in Kubernetes clusters, or in external environments hosted by trusted SaaS providers.

Limitations

The current material does not provide specific pricing, platform restrictions, performance metrics, or detailed usage steps; related content is not yet available.

Related tools

Browse category