Vectora MCP Server

What the code does

We read the source, 4 d ago · rules 995398eba69f

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

    "com confiança (ex.: rm -rf, git push --force, apagar recursos)."

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

            result = subprocess.run(  # nosec B603, B607

    re.compile(r"(id_rsa|id_dsa|id_ecdsa|id_ed25519)(\.pub)?$"),

                for child in sorted(m.iterdir(), key=lambda p: p.name.lower())

    if _should_install_terminal_signals(dict(os.environ), force_web=force_web):

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

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 -e 'COHERE_API_KEY=<COHERE_API_KEY>' -e 'TAVILY_API_KEY=<TAVILY_API_KEY>' -- uvx vectora-agent

{
  "mcpServers": {
    "vectora": {
      "command": "uvx",
      "args": [
        "vectora-agent"
      ],
      "env": {
        "COHERE_API_KEY": "<COHERE_API_KEY>",
        "TAVILY_API_KEY": "<TAVILY_API_KEY>"
      }
    }
  }
}

[mcp_servers.vectora]
command = "uvx"
args = ["vectora-agent"]
env = { COHERE_API_KEY = "<COHERE_API_KEY>", TAVILY_API_KEY = "<TAVILY_API_KEY>" }

{
  "mcpServers": {
    "vectora": {
      "command": "uvx",
      "args": [
        "vectora-agent"
      ],
      "env": {
        "COHERE_API_KEY": "<COHERE_API_KEY>",
        "TAVILY_API_KEY": "<TAVILY_API_KEY>"
      }
    }
  }
}

{
  "servers": {
    "vectora": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "vectora-agent"
      ],
      "env": {
        "COHERE_API_KEY": "<COHERE_API_KEY>",
        "TAVILY_API_KEY": "<TAVILY_API_KEY>"
      }
    }
  }
}

Put your own values in place of <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). The author’s registry entry marks them as required.

Optional settings from the registry entry, left out of the block above: GOOGLE_API_KEY (Google Gemini API key (recommended free-tier LLM provider)), 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)).