Infino AI MCP Server

by infino-aiio.github.infino-ai/mcp-serverv0.16.0

Retrieval over your own data with Infino (BM25 full-text, vector, hybrid and SQL), an embedded engine on Apache Parquet over object storage.

0Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active9d ago

Install Infino AI MCP server

claude mcp add infino-ai -- npx -y @infino-ai/mcp-server

{
  "mcpServers": {
    "infino-ai": {
      "command": "npx",
      "args": [
        "-y",
        "@infino-ai/mcp-server"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "infino-ai": {
      "command": "npx",
      "args": [
        "-y",
        "@infino-ai/mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "infino-ai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@infino-ai/mcp-server"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "infino-ai": {
      "command": "npx",
      "args": [
        "-y",
        "@infino-ai/mcp-server"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
INFINO_MCP_URI	—	—	Data to serve: a local path, an s3://\|az:// bucket URI, or a hosted https://<host>/<database> endpoint (Infino Cloud). Optional — defaults to a durable per-user directory (~/.infino/mcp) so data persists across restarts, falling back to an ephemeral memory:// catalog only if that directory can't be created.
INFINO_API_KEY	—	—	API key for a hosted (https://) Infino Cloud endpoint. Required when INFINO_MCP_URI is an https:// URI; ignored for local and object-storage connections.
INFINO_MCP_EMBED_PROVIDER	—	—	Embedding provider: 'local' (Hugging Face transformers.js, default) or 'openai' (any OpenAI-compatible /embeddings endpoint, including Azure OpenAI's /openai/v1 surface). Inferred as 'openai' when INFINO_MCP_EMBED_BASE_URL is set.
INFINO_MCP_EMBED_BASE_URL	—	—	Base URL of the OpenAI-compatible embeddings API (e.g. https://api.openai.com/v1 or https://<resource>.openai.azure.com/openai/v1). Required when the provider is 'openai'; the server POSTs to <base>/embeddings.
INFINO_MCP_EMBED_API_KEY	—	—	API key for the 'openai' provider. Sent as both Authorization: Bearer and api-key so one value works for OpenAI and Azure OpenAI.
INFINO_MCP_EMBED_MODEL	—	—	Embedding model. local: a Hugging Face feature-extraction model (default Xenova/all-MiniLM-L6-v2, 384-dim). openai: the model/deployment name (e.g. text-embedding-3-small, 1536-dim). Must match the model that produced the table's stored vectors.
INFINO_MCP_VALIDATE	—	—	Set (1/true/yes) to probe the object store at startup, so bad credentials or an unreachable bucket fail then instead of on the first search.