mcpField
P
Politicians by Jev

Politicians by Jev

Remote
politiciansbyjev.vercel.appGames & Entertainment0Updated today

About Politicians by Jev

Politicians by Jev is an open-source demo that scores 100 well-known U.S. politicians against a question and surfaces the top match. It is for people exploring Jev's decision model and exposes the same asking and listing functions through an API and MCP server.

Key features

  1. 01Scores 100 politicians for a question
  2. 02Shows a top pick and runners-up
  3. 03Publishes verdict thresholds and methodology
  4. 04Provides a JSON API and share cards

Use cases

  1. 01Explore how Jev ranks politicians for a question
  2. 02Retrieve politician rankings from an agent
  3. 03Review the model's verdict thresholds

MCP support

The Streamable HTTP MCP server provides `ask_jev` and `list_politicians` tools. It applies the same guardrails and rate limit as the website.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://politiciansbyjev.vercel.app/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Jev! · politicians by Jev

An open-source demo of Jev, TypeSafe AI's decision model, on Vercel AI Gateway. America's 100 most famous politicians sit in a physics pile. Ask a question and Jev scores every one of them (100 yes/no calls, under a second); the top pick floats out, runners-up follow, and everyone who missed turns gray.

Live: https://politiciansbyjev.vercel.app · Methodology: https://politiciansbyjev.vercel.app/how-it-works

  • Thresholds and verdict rules: lib/verdict.ts (80% sure, 55% thinks so, 40% best guess)
  • Jev calls, question sorting, guardrails, and the shared 30-day answer store: lib/answer.ts
  • Per-question share card: app/og/route.tsx
  • The people: data/politicians.json; portraits saved by node scripts/fetch-faces.mjs

Use it from an agent

  • JSON API: GET https://politiciansbyjev.vercel.app/api/v1/ask?q=Best%20president%20ever (or POST {"question": "..."})
  • MCP server (Streamable HTTP): https://politiciansbyjev.vercel.app/api/mcp, tools ask_jev and list_politicians
  • Same guardrails and rate limit (20 a minute) as the site; see /llms.txt

Run it

npx vercel link && npx vercel env pull .env.local
npm run dev

AI Gateway auth uses the Vercel OIDC token, so no API key is needed.

License

Code: MIT (see LICENSE). Portraits: each under its own license, credited in CREDITS.md.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.