1
Add it to Claude Code
claude mcp add -e "GRAPH_API_KEY=${GRAPH_API_KEY}" predictfun-mcp -- npx predictfun-mcpRequired:
GRAPH_API_KEY+ 1 optionalEnvironment Variables
Set these before running Predict.fun MCP.
VariableDescriptionRequired
GRAPH_API_KEYAPI key from Subgraph Studio for querying The Graph GatewayYesMCP_HTTP_PORTCustom port for SSE transportNoAvailable Tools (2)
Once configured, Predict.fun MCP gives your AI agent access to:
get_platform_statsProvides a full platform overview including volume, open interest, yield, and sync status.get_top_marketsRanks markets by volume, open interest, or trade count.sort_byTry It Out
After setup, try these prompts with your AI agent:
→What is the current total volume and open interest on Predict.fun?
→Can you list the top 5 markets currently ranked by open interest?
→Provide a summary of the latest yield-bearing mechanics and reward distributions on the platform.
→Show me the current sync status of the Predict.fun subgraphs.
Prerequisites & system requirements
- An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
- Node.js 18+ with npm/npx installed
GRAPH_API_KEY— API key from Subgraph Studio for querying The Graph Gateway
Conare · memory for coding agents
Keep this setup from going cold
Save the docs, env vars, and workflow around Predict.fun MCP in Conare so Claude Code, Codex, and Cursor remember it next time.
Remember this setup$npx conare@latest