Vectora MCP Server

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add vectora -- uvx vectora-agent

{
  "mcpServers": {
    "vectora": {
      "args": [
        "vectora-agent"
      ],
      "command": "uvx"
    }
  }
}

[mcp_servers.vectora]
command = "uvx"
args = ["vectora-agent"]

{
  "mcpServers": {
    "vectora": {
      "args": [
        "vectora-agent"
      ],
      "command": "uvx"
    }
  }
}

{
  "mcpServers": {
    "vectora": {
      "args": [
        "vectora-agent"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: GOOGLE_API_KEY (Google Gemini API key (recommended free-tier LLM provider)), COHERE_API_KEY (Cohere API key — required for RAG embeddings and reranking), TAVILY_API_KEY (Tavily API key — required for web search and URL extraction), OPENAI_API_KEY (OpenAI API key (optional — alternative LLM provider)), ANTHROPIC_API_KEY (Anthropic API key (optional — alternative LLM provider)), LANGSMITH_API_KEY (LangSmith API key (optional — tracing and observability)). The author declared them in the registry entry; get the values from the project itself.