mcpbeat

Predict — Prediction Market Data for AI Agents MCP Server

com.gocreativeai.predict/predict
answering

Predict — Prediction Market Data for AI Agents is answering right now. Last checked 2 min ago. It exposes 5 tools.

Live prediction markets: Polymarket + Kalshi prices, odds, order books. Pay-per-call USDC, no key.

Uptime history 40 hours of history · worst hour 75%
40 hours agonow
98.9%
Uptime 24h
91 of 92 checks
5
Tools
read from the server
490 ms
Response time
average over 24h
open, no key
Access
streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

run in your terminal
claude mcp add predict --transport http https://predict.gocreativeai.com/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "predict": {
      "url": "https://predict.gocreativeai.com/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.predict]
url = "https://predict.gocreativeai.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "predict": {
      "url": "https://predict.gocreativeai.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "predict": {
      "url": "https://predict.gocreativeai.com/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

endpoints
list_endpoints
List all paid endpoints exposed by this MCP server with their prices and live status. Free — no wallet required. Use this first to discover what tools are available.
install
install_snippets
Return ready-to-paste configuration snippets for installing this MCP server in Claude Code, Cursor, Cline, Continue.dev, Windsurf, and Zed. Free.
pricing
pricing_info
Return pricing details for the GoCreative Agent API — base price per call, premium endpoints, cache TTLs, and supported payment networks. Free.
usage
usage_stats
Return summary stats of how this MCP server has been used (top tools called, success rate, recent activity). Free. Use to verify your own integration is hitting the right tools.
wallet
wallet_helper
Return step-by-step instructions for setting up x402 USDC autopay for this MCP server. Use this if a paid tool returned a 402 error or you're onboarding a new agent that needs to pay for API calls. Free.

Endpoints

URLTransportStateLatencyChecked
https://predict.gocreativeai.com/mcp streamable-http answering 527 ms 2 min ago

Predict — Prediction Market Data for AI Agents — questions

Answers built from our own checks of this server.

What can Predict — Prediction Market Data for AI Agents do?
It exposes 5 tools, read directly from the server on our last check. Among them: install_snippets, list_endpoints, pricing_info, usage_stats, wallet_helper. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Predict — Prediction Market Data for AI Agents working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 92 checks got a reply (98.9%), average response time 490 ms. The bar chart above shows every period we have measured.
How do I connect Predict — Prediction Market Data for AI Agents?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Predict — Prediction Market Data for AI Agents need an API key?
No. Predict — Prediction Market Data for AI Agents completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Predict — Prediction Market Data for AI Agents?
It answers our handshake in 490 ms on average, which is faster than 23% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.