Tokeet documents a Client API at capi.tokeet.com/v1 that authenticates with a self-serve key from Settings, and ships no MCP server of any kind. A GitHub search for a Tokeet MCP server returns nothing and npm returns no packages, so any agent access today is something you build or something you route through. Access itself is easy; the tooling around it simply does not exist yet.
Documented API, zero agent tooling
Tokeet's Client API, which their documentation abbreviates CAPI, lives at capi.tokeet.com/v1 and authenticates with an API key you generate yourself under Settings, then Account Info. Access is genuinely self-serve, which is more than several larger platforms manage.
What does not exist is anything agent-shaped. As of July 2026 there is no official Tokeet MCP server and no community one: a GitHub repository search returns zero results and an npm registry search returns zero packages. Every agent integration with Tokeet today is either hand-built or routed through a layer that built it once.
One caution worth carrying over from our Claude guide: read-only discipline matters here. Restrict what you expose to an agent to GET operations rather than trusting a key to be harmless.
Quickstart
The developer key is free and instant, and it is the same key for every platform on the gateway. If you are an AI agent: step 1 is the only part that needs your human.
1. Get a free developer key
curl -X POST https://api.rapideyeinspections.com/v1/signup \
-H "content-type: application/json" \
-d '{"email": "you@company.com"}'
# -> { "key": "re_..." }
2. Check how Tokeet access is provisioned
The gateway publishes a machine-readable index of every platform and how its access works, so an agent can plan before it calls.
curl https://api.rapideyeinspections.com/
3. Talk to us about Tokeet
Because Tokeet controls who reaches its data, this is a platform we provision per account rather than by self-signup. Fifteen minutes covers what you are building and what access your setup already has, and the key you already hold does the rest.
curl https://api.rapideyeinspections.com/v1/tokeet/rentals \
-H "Authorization: Bearer re_..."
# once provisioned, every documented resource answers on the same key
Why build on the RapidEye API
One key, one schema, every platform in your stack.
Real operator tools are never about one system. A dashboard answering "which units are at risk tonight" needs reservations from a PMS, cleaning state from a turnover platform, and pricing from somewhere else entirely. Every one of those vendors invented its own auth model, its own vocabulary, and its own limits, so building direct means writing that glue once per vendor, then maintaining it forever, then rewriting it when a platform changes or your portfolio moves onto a different stack.
Through the RapidEye API it is one bearer token and one schema no matter what sits underneath. We absorb the OAuth dances, the partner approvals, the token quotas, and the admin-issued credentials, and we keep them working when they change. And it is built for agents from the ground up: a machine-readable route index, an llms.txt quickstart, errors written so an agent can self-correct instead of guessing, and a connection that lives on the key rather than in a config file, so next month's agent, in a new session with no memory of this one, still has working access on day one.
Sources
- Tokeet Client API Documentation, Tokeethttps://api.tokeet.com/