Alpha Arcade

20 tools. 8 can modify or destroy data without limits.

8 destructive tools with no built-in limits. Policy required.

Last updated:

8 can modify or destroy data
12 read-only
20 tools total

Community server · catalogue entry verified 12/06/2026

How to control Alpha Arcade ↓

What Alpha Arcade exposes to your agents

Read (12) Write / Execute (0) Destructive / Financial (8)
Critical Risk

The most dangerous Alpha Arcade tools

8 of Alpha Arcade's 20 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Alpha Arcade

PolicyLayer is an MCP gateway — it sits between your AI agents and Alpha Arcade, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default
{
  "amend_order": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations
{
  "cancel_order": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations
{
  "get_agent_guide": {
    "limits": [
      {
        "counter": "get_agent_guide_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Alpha Arcade — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON ALPHA ARCADE →

Free to start. No card required.

All 20 Alpha Arcade tools

READ 12 tools
Read get_agent_guide Returns the Alpha Arcade agent guide — data model, units, orderbook mechanics, workflows, and common pitfalls. Read get_full_orderbook Fetch the full processed orderbook snapshot from the Alpha REST API for a market. Requires ALPHA_API_KEY. Inpu Read get_live_markets Fetch all live markets. Returns summary: id, title, marketAppId, prices, volume. Multi-choice markets have an Read get_market Fetch full details for a single market by ID (app ID string for on-chain, UUID for API). Returns the complete Read get_open_orders Fetch all open orders for a wallet on a specific market. You must provide walletAddress or set ALPHA_MNEMONIC. Read get_orderbook Fetch the on-chain orderbook as a unified YES-perspective view. Merges all 4 sides (YES bids/asks + NO bids/as Read get_positions Fetch all YES/NO token positions for a wallet across all markets. You must provide walletAddress or set ALPHA_ Read get_reward_markets Fetch all reward markets from the Alpha REST API. Returns markets that have liquidity rewards (totalRewards, r Read stream_live_markets Collect real-time market probability changes via WebSocket for a specified duration. Returns all accumulated c Read stream_market Watch a single market by slug via WebSocket and return the first change event. Times out if no change occurs. Read stream_orderbook Get a real-time orderbook snapshot for a market via WebSocket. Faster than on-chain reads (~5s vs ~10s). Retur Read stream_wallet_orders Watch a wallet for order changes via WebSocket and return the first change event. Times out if no orders chang

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Alpha Arcade

Can an AI agent move money through the Alpha Arcade MCP server? +

Yes. The Alpha Arcade server exposes 7 financial tools including amend_order, claim, propose_match. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the Alpha Arcade MCP server? +

Yes. The Alpha Arcade server exposes 1 destructive tools including cancel_order. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Alpha Arcade MCP server expose? +

20 tools across 3 categories: Destructive, Read, Write. 12 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Alpha Arcade? +

Register the Alpha Arcade MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Alpha Arcade tool call.

Deterministic rules across all 20 Alpha Arcade tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

20 Alpha Arcade tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.