Jev · BridgeheadJev × Claude · ChatGPT
Typed decisions, right in your chat.
On your own Jev key.
Jev answers with a typed, calibrated decision (a choice, a score, a yes or no with its probability), but there's no official way to reach it from claude.ai, ChatGPT, the phone or voice; the community servers run on your own computer, or hold your key for you. Jev · Bridge is a connector you add once: sign in, your Jev key goes into Bridgehead's vault, and Jev's choices, scores and yes/no checks are tools in your chat, with ranking and questions over a PDF or text file on top.
Copy. Paste. Connected.
How to connect it
Claude
claude.ai, the desktop app or the phone: Customize → Connectors → Add → Custom connector, then paste this.
https://jevbridge.fyi/mcpClaude Code
One line in your terminal.
claude mcp add --transport http jevbridge https://jevbridge.fyi/mcpChatGPT
In settings, turn on developer mode and add a custom app with this address.
https://jevbridge.fyi/mcpYour Jev key
Sign in when your chat asks, then add your Jev API key from TypeSafe's console once. You pay TypeSafe directly.
Add your Jev keyQuestions
What can Jev do in my chat?
Pick one of up to 255 options, rate on a scale you describe, or answer yes or no, each with its probabilities; several questions over one text in one call; rank many candidates against a query; and answer your questions over a PDF or text file. Set a threshold, and an answer below it comes back as unsure instead of a guess. Save a set of questions under a name and reuse it on any text or file (a résumé screen and a contract check come built in), and let an agent ask the gate before it runs a command or edits a file: allow, ask or block, with the reasons.
Is my Jev key safe?
It's checked with TypeSafe, kept encrypted in Bridgehead's vault and used only to call Jev for you. You pay TypeSafe directly; remove the key at any time at jevbridge.fyi/key.
Can Jev read my documents?
PDFs with a text layer, and text files, today: Bridgehead reads the file and asks your questions over it, a long document in two stages. Scans, pictures, audio and video come later.