alpha-arcade-mcp

alpha-arcade-mcp is a skill for Claude Code, Codex from phara23/alpha-mcp. It costs 71 tokens per session (2,295 once invoked), scanned A, original, MIT.

A connection to Alpha Arcade, a prediction-market service on the Algorand blockchain where people trade shares tied to possible outcomes.

In plain words
What is it for?
Browsing prediction markets and orderbooks, placing or changing trades, managing positions, splitting or merging shares, and claiming winnings.
Why use it?
It puts market data, orders, positions, and winnings in one agent-accessible interface instead of requiring separate website and blockchain operations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Browsing prediction markets and orderbooks, placing or changing trades, managing positions, splitting or merging shares, and claiming winnings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phara23/alpha-mcp/alpha-arcade-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add phara23/alpha-mcp --skill alpha-arcade-mcp
Clone the repo
git clone --depth 1 https://github.com/phara23/alpha-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for alpha-arcade-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/phara23/alpha-mcp/alpha-arcade-mcp/github.svg)](https://agentmods.dev/skills/phara23/alpha-mcp/alpha-arcade-mcp)
Your own site
<a href="https://agentmods.dev/skills/phara23/alpha-mcp/alpha-arcade-mcp"><img src="https://agentmods.dev/badge/skills/phara23/alpha-mcp/alpha-arcade-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for alpha-arcade-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/phara23/alpha-mcp/alpha-arcade-mcp"><img src="https://agentmods.dev/badge/skills/phara23/alpha-mcp/alpha-arcade-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,295 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.02295
Opus 5 $0.00036 $0.01148
Sonnet 5 $0.00014 $0.00459
Haiku 4.5 $0.00007 $0.00230

Measured 9d ago against content hash 30ab24ddc402, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

alpha-arcade-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/alpha-arcade-mcp/SKILL.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alpha Arcade — Prediction Markets on Algorand

Interact with Alpha Arcade prediction markets via the Alpha Arcade MCP server (16 tools across read-only, trading, and streaming categories).

Key Characteristics

  • On-chain prediction markets — all orders and settlements happen on Algorand
  • Binary and multi-choice markets — bet on YES/NO outcomes or choose from multiple options
  • USDC-denominated — all collateral and payouts in USDC (ASA 31566704)
  • Microunit inputs — all prices and quantities in tool inputs use microunits (1,000,000 = $1.00 or 1 share)
  • Formatted outputs — read tools return human-readable strings or API snapshot JSON depending on the tool

Setup

The Alpha Arcade MCP server requires environment variables:

Variable Required Description
ALPHA_MNEMONIC For trading Algorand wallet mnemonic (25 words)
ALPHA_API_KEY For reward markets and full API orderbooks Alpha Arcade API key
ALPHA_ALGOD_SERVER No Algod endpoint (default: mainnet Algonode)
ALPHA_INDEXER_SERVER No Indexer endpoint (default: mainnet Algonode)
ALPHA_MATCHER_APP_ID No Matcher app ID (default: 3078581851)
ALPHA_USDC_ASSET_ID No USDC ASA ID (default: 31566704)
ALPHA_API_BASE_URL No API base URL (default: https://platform.alphaarcade.com/api)

Read-only tools (browsing markets, orderbooks, positions) work without ALPHA_MNEMONIC. Trading tools require it.

Units

All prices and quantities in tool inputs use microunits: 1,000,000 = $1.00 or 1 share.

Human value Microunit value
$0.50 500,000
$0.05 slippage 50,000
1 share 1,000,000
30 shares 30,000,000

Tool outputs from read tools (get_orderbook, get_full_orderbook, get_open_orders, get_positions) return either pre-formatted summaries or raw JSON snapshots. Write tools accept raw microunit integers.

Market Data Model

Binary markets

A standard yes/no market has a single marketAppId, yesAssetId, and noAssetId. Use marketAppId for all trading calls.

Read the full file on GitHub · 176 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 176 lines · 71 tokens per session scan A 30ab24ddc402

Subscribe to this mod's changes

alpha-arcade-mcp is a skill published in the GitHub repository phara23/alpha-mcp (10 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 2,295 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.