ToolHive is an open-source platform for running and governing Model Context Protocol servers and agent skills. Its runtime launches MCP servers in isolated containers and supports fine-grained permissions, network filtering, secrets management, proxying for remote servers, and OpenTelemetry or Prometheus observability. Developers can use a cross-platform desktop app or CLI for local workflows, while platform teams can deploy the Kubernetes Operator for shared, multi-user environments. The broader architecture combines a runtime, a Registry Server for curated catalogs, a Virtual MCP gateway for centralized authentication and tool routing, and desktop or web portals for discovery and installation. ToolHive is the Apache-2.0 open-source core; Stacklok Enterprise is a separate hardened distribution with centralized management, turnkey identity integrations, hardened images, and support. ToolHive is best for teams that need a self-hosted MCP operations and governance layer across local and Kubernetes environments. It is not primarily a vulnerability scanner or a tool for authoring individual MCP servers, and teams that only need to inspect one server may prefer a narrower inspector.
ToolHive
Run and govern MCP servers across desktop, CLI and Kubernetes
Open-source MCP runtime and governance platform that runs servers in isolated containers, curates registries, enforces access policies, and operates gateways across desktop, CLI, and Kubernetes.
Pricing
Free and open source under Apache-2.0 with no ToolHive license fee; users provide their own container or Kubernetes infrastructure. Stacklok Enterprise pricing is not published and requires a demo or direct contact.
Platforms
Desktop app and CLI for macOS, Windows and Linux, plus a Kubernetes Operator for shared environments; local servers use compatible container runtimes, with registry, gateway, runtime and portal components.
Categories
Tags
Use Cases
Alternatives
Docker MCP Gateway
Open-source Docker gateway for containerized MCP server orchestration
Docker MCP Gateway is Docker's open-source orchestration layer for Model Context Protocol servers. It gives MCP clients one gateway, launches catalog servers in isolated containers on demand, injects credentials, applies runtime restrictions, and routes tool requests. Catalogs and profiles let teams reuse approved server collections across clients, while Docker Desktop can run the gateway automatically with MCP Toolkit enabled.
mcp-proxy
Protocol bridge converting MCP stdio transport to HTTP/SSE endpoints
mcp-proxy is a protocol bridge that converts MCP servers using stdio transport into HTTP and Server-Sent Events endpoints accessible over the network. This enables remote MCP server hosting, load balancing, and sharing servers across multiple AI clients. Supports both directions: wrapping stdio servers with HTTP and connecting to remote SSE servers through local stdio. Over 2,400 GitHub stars.
Related Tools
MCPJam Inspector
Test and debug MCP servers before they ship
Open-source platform for inspecting, debugging and regression-testing MCP servers, MCP Apps and ChatGPT apps, with OAuth and protocol conformance for local and CI workflows.
Anamorpher
Craft image-scaling prompt-injection payloads to red-team multimodal AI systems
Open-source red-team toolkit from Trail of Bits that generates image-scaling attack payloads — images that look benign at full resolution but reveal a hidden prompt injection after a multimodal system downsamples them.
Grafana MCP Server
First-party MCP server for querying and managing Grafana
Grafana's official Model Context Protocol server, letting AI assistants search dashboards, query datasources, and manage alerts/incidents on your Grafana instance through a standard MCP interface.
MCP Registry
Official open catalog of Model Context Protocol servers
The official, community-run registry for discovering and publishing Model Context Protocol (MCP) servers — an open index that MCP clients read to find available servers.
CAI (Cybersecurity AI)
AI agent framework for offensive security and penetration testing
Alias Robotics' agent framework for building AI-driven offensive-security workflows — reconnaissance, exploitation, privilege escalation, and lateral movement — with multi-agent handoffs and human-in-the-loop control. Source-available, but the core is licensed for non-commercial research use only.
Figma Console MCP
Turn a Figma design system into a programmable API for AI assistants
Figma Console MCP is open-source design-system infrastructure that exposes Figma to AI assistants through MCP. It supports structured extraction, design creation and editing, debugging, accessibility audits, and bidirectional design-token workflows across local, remote read-only, and paired cloud modes; it is not a generic one-click Figma-to-code exporter.