Built on Solana“I need my agent to use the Stripe, Jupiter, whatever-is-next API.”
One line adds it. No client to hand-write.
Open source · Built in public
Give your agent
any API. Never expose your keys.
Gecko turns any API into tools your agent calls right the first time. Your key is injected only at the moment of the call, sent only to the API's own host. Never in your files, never in the agent's context.
Try it now
$ npx @geckovision/gecko add <your-api>gecko — add
THE JOURNEY
You have felt this before. Every API, every agent.
“Do I paste my API key into mcp.json? Into an env var?”
Neither. Your key stays in your keychain and is injected only at the moment of the call. Never in a file, never in the agent's context.
“The agent called it and got a 400. Then a 401. Then another 400.”
Gecko read the API first. Your agent calls it right the first time: right params, right auth.
“I don't want to burn rate limits or real money just to test.”
Recorded mode proves every call offline, for $0.
“It worked yesterday. Now it's a 401 at 3am. Who wrote a refresh loop?”
Sessions auto-refresh. The agent never sees the expiry.
“Fifth API, same pain, times five.”
One layer for every API. Keys out of reach, calls correct, no per-API glue.
For agent builders
Any API in your agent's hands. Your keys nowhere near it.
- One command adds any OpenAPI to your agent as intent-shaped tools.
- Your key stays in the keychain, injected at call time. Never in a prompt.
- $0 recorded mode proves every call offline before a live request.
For API providers
Make your API the one agents call right.
- First-call-correct MCP tools, no integration code needed.
- Wire to x402 and every correct call settles. You keep 100%.
- Flat monthly fee per API. Never a take-rate.
WHY NOW
The keys are already leaking.
- 28.65M
- new hardcoded secrets on public GitHub in 2025, up 34% in a year(GitGuardian)
- ~2×
- AI-assisted commits leak secrets at about twice the base rate(WorkOS)
- 24,008
- secrets found hardcoded in MCP config files on public GitHub(Ajay Raj Singh S.)
- 90%
- of orgs letting humans share credentials with agents expect to spend on undoing it by 2028(Gartner)
- 82.5%
- of Crypto and Web3 docs traffic is already agents(Mintlify)
- 857
- tests green, live end to end on the TxODDS World Cup API(Gecko)
HOW IT WORKS
Three steps between your agent and any API.
01
CONNECT
Point Gecko at the API.
An OpenAPI spec or a docs URL. Even messy, undocumented, or paywalled. Gecko comprehends the surface into tools your agent picks by intent.
02
SECURE
Your key goes in the keychain.
Gecko holds session state in the control plane. The credential stays local, resolved only inside your runner.
03
EXECUTE
The agent calls. Auth appears at the wire.
The call is assembled correctly the first time. The key is injected at the moment of the call and sent only to the API's own host. Sessions auto-refresh.
Control plane only. The key never enters the agent, the model, your files, or Gecko's servers.
FAQ
Questions, before you install.
Where does my key actually live?+
In your keychain. Gecko resolves it in your local runner and injects it at the moment of the call, host-pinned to the API's own domain. It never enters the agent's context, your files, or Gecko's servers.
What can Gecko see?+
The API surface and tool definitions. Control plane only: never your response payloads, your data, or your secrets.
What if my API has no OpenAPI spec?+
We read the docs. For Mintlify, Redoc, and Scalar we discover the spec behind the page. If we can't find one, we tell you what to paste.
Is it free?+
The engine is open source and free. Providers pay a flat per-API fee, never a take-rate.
Does it work outside Claude Code?+
Yes. Cursor or any MCP client via the hosted endpoint, or as a Python library with recorded mode ($0) or live.
How is this different from an MCP wrapper?+
Wrappers pass raw complexity and leave auth to you. Gecko comprehends the surface, injects credentials at the wire, and keeps sessions alive.
This page has a twin your agent can read. For agents →