MCP Server
MCP
io.github.brunosrz/vectora
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
Install
uvx vectora-agent
Configuration Example
{
"remotes": [],
"packages": [
{
"registryType": "pypi",
"identifier": "vectora-agent",
"version": "0.1.0rc3",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Google Gemini API key (recommended free-tier LLM provider)",
"format": "string",
"isSecret": true,
"name": "GOOGLE_API_KEY"
},
{
"description": "Cohere API key — required for RAG embeddings and reranking",
"isRequired": true,
"format": "string",
"isSecret": true,
"name": "COHERE_API_KEY"
},
{
"description": "Tavily API key — required for web search and URL extraction",
"isRequired": true,
"format": "string",
"isSecret": true,
"name": "TAVILY_API_KEY"
},
{
"description": "OpenAI API key (optional — alternative LLM provider)",
"format": "string",
"isSecret": true,
"name": "OPENAI_API_KEY"
},
{
"description": "Anthropic API key (optional — alternative LLM provider)",
"format": "string",
"isSecret": true,
"name": "ANTHROPIC_API_KEY"
},
{
"description": "LangSmith API key (optional — tracing and observability)",
"format": "string",
"isSecret": true,
"name": "LANGSMITH_API_KEY"
}
]
}
]
}
mcp
model-context-protocol
pypi
By
Comments
Sign in to leave a comment