Trusty Squire signs up / in to websites for you so you don’t have to.
Browser operators often stop at signup walls and bot detection. Trusty Squire opens the real website, completes signup or sign-in, finishes setup, and saves generated credentials without putting them in chat, code, or .env.
- 01“Sign up for Braintrust and save its API key outside agent context.”
- 02“Set up Cerebras inference without putting its API key in this project.”
- 03“Sign up for Clerk, create an app, and save the secret key.”
- 04“Create a DeepInfra account and wire the vaulted token into my backend.”
- 05“Sign up for Zilliz Cloud and keep its API key out of .env.”
- 06“That app token leaked. Revoke its access now.”
What is Trusty Squire?
Trusty Squire is an MCP server for coding agents. Claude Code, Codex, Cursor, OpenCode, or Goose plans the job; Trusty Squire operates the website and keeps the generated secret on the safe side of the boundary.
How does it work?
- Your agent names the website and the finished outcome.
- Trusty Squire drives the real signup, sign-in, or setup flow.
- The credential is encrypted in a write-only vault and injected server-side when used.
If a site requires a phone, hard CAPTCHA, payment, or a decision only you should make, the run stops and tells you instead of guessing.
Your agent handles signups
Ask for a service. Your squire creates the account, works through available verification, and stores the generated API key. No fifteen-tab signup detour, right inside Claude Code, Codex, OpenCode, Goose, and Cursor.
Use keys without exposing them
Stop scattering keys across .env files. Keys go into the vault; a proxy injects each value into the provider request server-side without returning it to the agent or consuming app.
Finish setup behind a login
Wire up OAuth across consoles, configure webhooks, and stand up projects. Your squire does the authenticated click-work while the secret stays out of chat.
Install the squire. Get back to building.
One command. Plugs into your agent of choice. Free to start.