Infino MCP Server

Fast search on object storage — SQL, full-text, and vector search.

Local serverstdioPython

What is the Infino MCP server?

Infino MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Fast search on object storage — SQL, full-text, and vector search.

What you get

The full Rust API reference is on docs.rs/infino.

What the assistant can call

Once Infino is connected, these are the calls the assistant has available:

  • Multi — modal queries** — keyword (BM25), vector, and SQL queries over the same rows, offering flexible query paths for agents
  • Object-storage-native — data lives on S3, Azure, GCS, or local disk, with snapshot-isolated reads and atomic commits
  • Backend — Keys
  • Azure — azure_storage_account_name, azure_storage_account_key, azure_storage_sas_key, azure_storage_client_id, azure_storage_client_secret
  • GCS — google_service_account (path), google_service_account_key (inline JSON), google_application_credentials, google_skip_signature

Setting it up

The server ships on npm as @infino-ai/infino, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Choosing this one

Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Infino's toolset — Multi, Object-storage-native, Backend and 2 more — is a fair guide to whether it matches your workflow. It is maintained by infinohq; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the infino mcp server does with a few real requests.

Available tools

ToolWhat it does
Multimodal queries** — keyword (BM25), vector, and SQL queries over the same rows, offering flexible query paths for agents.
Object-storage-nativedata lives on S3, Azure, GCS, or local disk, with snapshot-isolated reads and atomic commits.
BackendKeys
Azureazure_storage_account_name, azure_storage_account_key, azure_storage_sas_key, azure_storage_client_id, azure_storage_client_secret, azure_storage_tenant_id
GCSgoogle_service_account (path), google_service_account_key (inline JSON), google_application_credentials, google_skip_signature

How to install the Infino MCP server

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

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Infino to Multi.
  • Use Infino to Object-storage-native.
  • Use Infino to Backend.

Frequently asked questions

It connects Infino to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (Multi, Object-storage-native, Backend, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Infino directly.