Skip to main content
A data source is how Bag of words reaches your data. You point it at a database, a file share, or an application, tell it which tables or folders matter, and the agent queries it in place — no data movement, no copies. Each data source also carries the context that makes answers good: descriptions, instructions, conversation starters, and access rules.
In the product, a data source is also called an agent — the connection plus everything the AI knows about it. See Connecting a data source for the full setup flow.

​
Three kinds of connections

Data

Databases, warehouses, BI and semantic layers, observability platforms, and business applications. The agent sees tables and writes queries against them.

Files

File shares, object storage, and document libraries. The agent sees files, searches them, and reads their contents.

Integrations and tools

MCP servers and custom REST APIs. The agent sees tools it can call, each governed by an approval policy.
The distinction matters in three practical ways:
  • What the agent sees. Table-shaped sources produce SQL; file-shaped sources produce search and reads; tool-shaped sources produce tool calls that can require confirmation before they run.
  • Who owns the catalog. Most connections have one shared catalog an admin curates. Personal sources — OneDrive, Google Drive, a mailbox — have no shared catalog at all: each user’s own account is the catalog.
  • What per-user authentication costs. Per-user sign-in is included for file and tool connections. On database-style connections it requires an Enterprise license. See Authentication and access.

​
Data connectors

Databases, warehouses, BI tools, observability platforms, and business applications.

​
File connectors

File shares, object storage, and document libraries.

​
Integrations and tools

MCP servers, custom REST APIs, and mailbox connectors. Tool connections are governed by per-tool approval policies — see MCP connections. Bag of words also ships MCP presets — one-click tiles for Monday, Notion, Linear, Atlassian, GitHub, Sentry, Google Drive, and X. They all create a standard MCP connection with the server URL and OAuth settings pre-filled.

​
Editions

Connectors marked Enterprise require a license key (how to activate). Without one, they appear in the catalog with a lock. Connectors marked Beta work but may change; treat their field names as less stable than the rest.
Missing a connector? Open an issue or a PR at github.com/bagofwords1/bagofwords.

​
Where to go next

Connecting a data source

The setup flow: connect, choose tables, add context, and control access.

Authentication and access

Shared vs per-user credentials, OAuth, Kerberos SSO, and what needs Enterprise.

MCP connections

Connect any MCP server and govern its tools.

User context forwarding

Pass the caller’s identity to an MCP server on every call.