← Index

io.github.brunosrz/vectora

io.github.brunosrz/vectora·v0.1.0rc3·Filesystem
Quality Score
80
/100

AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.

§00  Trust verdict · v1 advisory ·  method
UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "vectora": {
      "command": "uvx",
      "args": [
        "vectora-agent"
      ],
      "env": {
        "GOOGLE_API_KEY": "<your-google_api_key>",
        "COHERE_API_KEY": "<your-cohere_api_key>",
        "TAVILY_API_KEY": "<your-tavily_api_key>",
        "OPENAI_API_KEY": "<your-openai_api_key>",
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "LANGSMITH_API_KEY": "<your-langsmith_api_key>"
      }
    }
  }
}
§02  Environment variables
GOOGLE_API_KEY
secret

Google Gemini API key (recommended free-tier LLM provider)

COHERE_API_KEY
requiredsecret

Cohere API key — required for RAG embeddings and reranking

TAVILY_API_KEY
requiredsecret

Tavily API key — required for web search and URL extraction

OPENAI_API_KEY
secret

OpenAI API key (optional — alternative LLM provider)

ANTHROPIC_API_KEY
secret

Anthropic API key (optional — alternative LLM provider)

LANGSMITH_API_KEY
secret

LangSmith API key (optional — tracing and observability)

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
10
installability
25
documentation
15
stability
5
§04  Alternatives in Filesystem