Una implementación de servidor de Protocolo de contexto de modelo (MCP) que se integra con Vectorize para la recuperación avanzada de vectores y extracción de texto.
export VECTORIZE_ORG_ID=YOUR_ORG_ID
export VECTORIZE_TOKEN=YOUR_TOKEN
export VECTORIZE_PIPELINE_ID=YOUR_PIPELINE_ID
npx -y @vectorize-io/vectorize-mcp-server@latestRelated MCP server: @sanderkooger/mcp-server-ragdocs
{
"mcpServers": {
"vectorize": {
"command": "npx",
"args": ["-y", "@vectorize-io/vectorize-mcp-server@latest"],
"env": {
"VECTORIZE_ORG_ID": "your-org-id",
"VECTORIZE_TOKEN": "your-token",
"VECTORIZE_PIPELINE_ID": "your-pipeline-id"
}
}
}
}Realizar búsquedas vectoriales y recuperar documentos (ver API oficial):
{
"name": "retrieve",
"arguments": {
"question": "Financial health of the company",
"k": 5
}
}Extrae texto de un documento y conviértelo en formato Markdown (consulta la API oficial):
{
"name": "extract",
"arguments": {
"base64document": "base64-encoded-document",
"contentType": "application/pdf"
}
}Genere una investigación profunda privada desde su canalización (consulte la API oficial):
{
"name": "deep-research",
"arguments": {
"query": "Generate a financial status report about the company",
"webSearch": true
}
}npm install
npm run devBifurcar el repositorio
Crea tu rama de funciones
Enviar una solicitud de extracción
This server cannot be deployed
An MCP server that gives your AI access to the source code and docs of all public github repos
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
