{
  "name": "io.github.BeehiveInnovations/zen-mcp-server",
  "description": "Zen MCP is an orchestration server that lets a primary model (typically Claude) delegate to other LLMs as sub-agents — Gemini, GPT, o-series, DeepSeek, local Ollama — through a unified `chat`, `thinkdeep`, `debug`, `analyze`, `codereview`, and `consensus` tool surface.",
  "status": "active",
  "version": "latest",
  "_meta": {
    "com.top-mcps/lastVerified": "2026-05-26",
    "com.top-mcps/score": {
      "value": 71,
      "rubricVersion": "2026-04",
      "lastComputed": "2026-05-26T10:50:23.743Z",
      "methodology": "https://top-mcps.com/about/methodology"
    },
    "com.top-mcps/stats": {
      "fetchedAt": "2026-05-26T10:50:23.602Z",
      "githubStars": 11563,
      "lastCommitAt": "2025-12-15T17:07:31Z"
    }
  },
  "repository": {
    "url": "https://github.com/BeehiveInnovations/zen-mcp-server",
    "source": "github"
  },
  "author": {
    "name": "Beehive Innovations (community)"
  },
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "zen-mcp-server",
      "version": "latest",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "name": "GEMINI_API_KEY",
          "description": "GEMINI_API_KEY — required credential for Zen MCP.",
          "isRequired": true,
          "isSecret": true
        },
        {
          "name": "OPENAI_API_KEY",
          "description": "OPENAI_API_KEY — required credential for Zen MCP.",
          "isRequired": true,
          "isSecret": true
        },
        {
          "name": "OPENROUTER_API_KEY",
          "description": "OPENROUTER_API_KEY — required credential for Zen MCP.",
          "isRequired": true,
          "isSecret": true
        }
      ]
    }
  ],
  "capabilities": {
    "security": {
      "scope": "network",
      "sandbox": "Calls outbound to whichever LLM providers you configure. Prompts and outputs flow through those providers under their privacy policies.",
      "gotchas": [
        "Multi-model calls amplify token spend — set per-provider budgets.",
        "Provider-specific features (Anthropic prompt caching) do not pass through universally."
      ]
    }
  },
  "_links": {
    "html": "https://top-mcps.com/mcp/zen-mcp",
    "markdown": "https://top-mcps.com/mcp/zen-mcp.md",
    "methodology": "https://top-mcps.com/about/methodology"
  }
}