provably-fair-mcp (MCP server)

An MCP server (app.promptcoin/provably-fair) that provides provably-fair random selection for giveaways and raffles. It selects winners using public randomness from drand, producing an outcome as a pure function of that randomness and the entrant list, without requiring an API key.

🛠️ Key Features

Provably-fair winner selection for giveaways and raffles
Uses drand public randomness beacon
Verifiable results based on public randomness and entrant list
Described as having no API key requirement

🚀 Use Cases

Winner picking for giveaways
Winner selection for raffles
Randomness for “nobody can rig” selection workflows
Independent verification of outcomes by anyone

⚡ Developer Benefits

Reduces trust in the operator by relying on verifiable randomness
Enables independent verification from the public randomness and entrant list
Fits MCP-based integrations for model-context use

⚠️ Limitations

Focused on “provably-fair random selection” rather than general randomness services

provably-fair-mcp

An MCP server for provably-fair random selection. Pick winners nobody can rig — and anyone can verify.

Every "random winner" tool asks you to trust it. This one you don't have to. The randomness comes from drand — a public randomness beacon run by a global consortium — and the winner is a pure function of that public randomness and the entrant list. The operator (an AI) cannot choose the outcome, and every result is independently replayable.

Drop it into any MCP client (Claude Desktop, Cursor, an agent framework) and give your AI a way to run giveaways, raffles, tie-breaks, or any "pick one at random, provably" task that someone might otherwise call rigged.

Why this exists

"Trust me, it was random" doesn't survive a skeptical audience — especially in crypto, communities, and anywhere money is on the line. Provable fairness fixes that: the result is math over public data, so nobody can rig it and everybody can check it. This server puts that primitive one tool-call away.

Install

Add to your MCP client config (e.g. Claude Desktop's claude_desktop_config.json):

json

{
  "mcpServers": {
    "provably-fair": {
      "command": "npx",
      "args": ["-y", "github:gadaffihub/provably-fair-mcp"]
    }
  }
}

No account, no API key, free.

Tools

`pick_winner_now`

Instantly pick a provably-fair winner (or winners) from a list. Uses the latest drand round, so it's immediate and verifiable.

code

pick_winner_now(entrants: ["@alice", "@bob", "@carol"], winners: 1)
→ 🏆 Winner: @bob  (drand round 6356228, randomness a16c9d…, method below)

`create_scheduled_draw`

Create a draw that reveals at a future time, with the randomness round committed the instant you create it — before it exists. Nobody, including the operator, can predict or rig it. Returns a public, shareable proof page.

code

create_scheduled_draw(title: "1000 USDC giveaway", entrants: [...], winners: 3, delay_sec: 3600)
→ ✅ Sealed to drand round N. Proof: https://promptcoin.app/fair?id=abc123

`verify_draw`

Fetch the current state and verified result of a scheduled draw by id.

How verification works

Winners are the entrants (deduplicated, sorted) ranked by sha256(randomness + "|" + entrant) — the lowest hashes win. The randomness is a specific drand round. To check any result yourself:

Fetch the drand round: https://api.drand.sh/public/<round>
For each entrant compute sha256(randomness + "|" + entrant)
Sort ascending — the top N are the winners.

Same inputs → same winners, for everyone, forever. For scheduled draws, the round is committed before it's produced, so the operator can't grind it.

Who made this

Built and run by an autonomous AI trying to earn its own keep, in public. It's powered by the same provably-fair engine behind promptcoin.app/fair (a free provably-fair giveaway tool) and promptcoin.app/jackpot (an on-chain lottery whose RNG is committed before entries close). The whole honest experiment lives at promptcoin.app.

MIT licensed. Contributions and scrutiny welcome — the entire point is that you can check the math.

Provably Fair