Platform / Access

Two ways in. One surface.

You should not have to change how you build to adopt a data layer. swarmsDB meets your agent where it already is — native MCP tools for an agent that speaks the protocol, a plain REST call for everything else — and both reach the identical capability surface.
mcp: app.swarmsdb.ai/mcp · rest: bearer + select=

Swarm phase Delivery — authorized transit: the canonical dataset flies to the agent; two ways in, one surface.

MCP

Connect an agent over MCP

Point an MCP-speaking agent — Claude, or your own — at the swarmsDB endpoint. It discovers the catalogue and calls it as native tools. This is the path a keyless OAuth connector uses, so no API key changes hands.

REST

Or call the REST surface directly

Prefer plain HTTP? The same capabilities answer to a REST call with a bearer token and a projection. Nothing about the response changes — you still get typed sections, not a raw upstream blob.

# claude_desktop_config.json — no API key changes hands
{ "mcpServers": {
    "swarmsdb": { "url": "https://app.swarmsdb.ai/mcp" }
} }
grant
{ "key_material": null,
  "grant": "workspace-bound",
  "revocable": true }
upstream 8,457,367 1,508 chars

Point one agent at it.

Connect over MCP or REST. If your agents read more than one source, the context bill is the first thing you will see move.