Deploy Now

SaaS Alternative

Toolhouse Composio Smithery

Categories

Developer Tools DevOps AI Infrastructure MCP Kubernetes Container Management

Stars

2,122

Forks

291

Watchers

15

Developer links

Last Updated: 09-08-2026
Share on X

ToolHive

ToolHive is an open-source MCP server management platform that lets you run, secure, and orchestrate Model Context Protocol servers in isolated containers, giving AI agents structured access to tools like GitHub, databases, and cloud services without exposing host credentials or network. Every server launches inside its own sandboxed container with a minimal permission file, network access filtering, and encrypted secrets management, preventing misbehaving connectors from reaching beyond their defined scope. The built-in registry provides a catalog of vetted servers you can install with one command, while custom images and package-manager references let you onboard proprietary connectors without writing Dockerfiles. Platform teams deploy the Kubernetes operator to declare MCP servers as cluster resources using Custom Resource Definitions, with automated lifecycle management and multi-namespace isolation. The Virtual MCP Server gateway aggregates multiple backends behind a single endpoint, centralizing OIDC authentication, tool filtering, and composite cross-server workflows so clients connect once instead of juggling separate URLs. An MCP Optimizer analyzes tool schemas via semantic search and surfaces only relevant tools per request, cutting token consumption by up to 85%. OpenTelemetry traces and Prometheus metrics deliver full visibility into tool execution, latency, and request audit trails across every managed server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

ToolHive
ToolHive
ToolHive
ToolHive
ToolHive

Benefits

  • Airtight Container Sandbox Per Server
  • Each MCP server runs in its own isolated container with a minimal permission file, network access controls, and encrypted secrets, preventing compromised connectors from accessing your host system or internal network.
  • One Gateway, Every Backend
  • Virtual MCP Server aggregates multiple backends behind one endpoint with centralized OIDC authentication, tool filtering, and cross-server composite workflows, so clients connect once instead of managing separate URLs.
  • Kubernetes-Native MCP Fleet Control
  • Declare MCP servers as Kubernetes resources via Custom Resource Definitions with automated pod creation, service discovery, ingress integration, and multi-namespace isolation for production-grade deployments.
  • Up to 85% Token Savings
  • The MCP Optimizer uses semantic schema analysis to surface only relevant tools per request, cutting token consumption dramatically compared to sending complete tool catalogs to AI agents.

Features

  • Container Runtime
  • Runs MCP servers in Docker or Podman containers with fine-grained permissions, network isolation, and automatic containerization of servers that lack official images.
  • Virtual MCP Server
  • Aggregates multiple MCP backends behind a single Streamable HTTP endpoint with OIDC/OAuth SSO, tool filtering, and multi-step composite workflows across servers.
  • Kubernetes Operator
  • Manages MCPServer, MCPRemoteProxy, and VirtualMCPServer as Kubernetes CRDs with automated lifecycle management, service creation, and Helm-based installation.
  • Built-in Registry
  • Curates a catalog of vetted MCP servers with provenance verification, server signing, and support for the official MCP Registry API specification.
  • Enterprise Observability
  • Emits OpenTelemetry traces and Prometheus metrics for tool execution, latency tracking, and request audit logging across all managed MCP servers.