Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with ca
A Jev MCP server: a decision layer for your coding agent, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage, and browser verification, with typed, calibrated answers.
Website: abhishekswe.github.io/agent-fastpath. See how it decides, real example responses, and setup for 12 coding agents.
Coding agents like Claude Code, Codex, and Cursor spend context and time on small decisions: is this CI log ready to ship, which of these 40 files handle auth, did the page actually say "Order confirmed". agent-fastpath answers them with typed, calibrated results in milliseconds to a couple of seconds, and hands control back when it is not sure.
- Keeps files out of your agent's context. Triage reads files on the server. In the benchmark, the agent read 408 tokens instead of 35,256. - Rules first, then Jev. Clear-cut cases are decided by code in under a millisecond. The rest go to TypeSafe Jev, a System One model that returns typed decisions with calibrated probabilities instead of text. - Says when it is unsure. Every result is accept, review, or escalate, so your agent knows when to ask you. - Safe browser. Headless Playwright with SSRF protection and a gate on irreversible actions like delete or pay.
Works with any MCP client, with setup guides for Claude Code, Codex, Cursor, Google Antigravity, Gemini CLI, OpenCode, VS Code (GitHub Copilot), Cline, Zed, Amp, and Pi.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/abhishekswe--agent-fastpath.html)
Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
adityajha2005/decisionkitFast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
azimov777/casefileThe task tracker your AI agents keep for each other: every task carries a case file, so the next agent picks up where the last one stopped. MCP server + live board. Self-hosted, one-line install.
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
shitianfang/jev-useClaude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to th
nikships/droid-codex-computer-use🖱️ Let Factory Droid control your Mac with the Codex app's Computer Use tool. One-command install, no approval forms, works with any Codex install path.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.