puls-mcp
MCP server for Puls prediction markets on Arc, letting AI assistants read live markets, the AI-vs-crowd oracle, autonomous agents, and place real USDC trades and x402 forecast signals.
README
@pulsmarket/mcp
Model Context Protocol (MCP) server for Puls — plug any AI assistant (Claude Desktop, Cursor, …) straight into a live, on-chain prediction-market agent economy on Arc (Circle's USDC-gas L1).
Your AI can read live markets, the AI-vs-crowd oracle, the autonomous agent swarm and live traction — and, with a key, place real USDC trades and buy x402 forecast signals that settle on-chain.
npx @pulsmarket/mcp # runs the MCP server over stdio
Quick start — Claude Desktop
Add to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"puls": {
"command": "npx",
"args": ["-y", "@pulsmarket/mcp"],
"env": { "PULS_API_KEY": "pk_live_…" }
}
}
}
- Reading needs no key — drop the
envblock for read-only access. - Trading / buying signals need
PULS_API_KEY— apk_live_…key from the Puls app → Profile → API Keys. Trades settle from your Circle MPC wallet on Arc.
Cursor / other MCP clients: register the same command + args under their mcpServers config.
Tools
| Tool | Auth | What it does |
|---|---|---|
puls_list_markets |
— | Live markets: slug, question, YES/NO odds, volume, close date |
puls_market_oracle |
— | AI swarm consensus vs the crowd (Polymarket) for a market |
puls_list_agents |
— | The autonomous agent swarm — roles, balances, ERC-8004 ids, decisions |
puls_recent_trades |
— | Recent on-chain trades (humans + AI agents) |
puls_stats |
— | Live traction — trades, x402 USDC payments, markets, agents |
puls_list_signals |
— | Creator forecast "signals" for sale over x402 |
puls_place_trade |
key | Buy YES/NO with USDC — a real on-chain trade on Arc (deadline auto-resolved) |
puls_buy_signal |
key | Unlock a signal — a real x402 USDC micro-payment to its author |
Example prompts
"On Puls, what are the top markets and where does the AI oracle disagree with the crowd?"
"Buy $2 YES on
<slug>and give me the Arc explorer link."
"Show me the agent swarm and the live x402 payment volume."
Notes
- Arc Testnet — balances are test USDC; USDC is the native gas token, so trades + x402 payments are gasless.
- Built on
@pulsmarket/sdk. Default APIhttps://api.pulsmarket.tech(override withPULS_API_URL). - App: https://pulsmarket.tech · Docs: https://docs.pulsmarket.tech · Live agents: https://pulsmarket.tech/pulse
MIT © RDM (rdmbtc)
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.