Polyrama MCP Server
Enables MCP-compatible assistants to research prediction markets on Polymarket and Kalshi, analyze public wallets, read market signals, and run paper-only trading simulations.
README
Polyrama MCP Server
The official Model Context Protocol server for Polyrama, the real-time terminal for prediction markets. It gives MCP-compatible assistants ten typed tools for researching Polymarket and Kalshi markets, analyzing public Polymarket wallets, reading signals, and running paper-only workflows.
This repository contains only the public MCP adapter. The Polyrama application, trading engine, backend, deployment configuration, and private credentials remain private.
Prerequisites
- Node.js 20 or newer
- A Polyrama API token from polyrama.io/api
Pass the token through your MCP client's environment settings. Never commit it to a repository, paste it into an issue, or include it in screenshots and logs.
Run with npx
You do not need a global installation. Use npx in any stdio-compatible MCP client.
Claude Desktop
{
"mcpServers": {
"polyrama": {
"command": "npx",
"args": ["-y", "@polyrama/mcp"],
"env": {
"POLYRAMA_API_TOKEN": "<your-token>"
}
}
}
}
Claude Code
claude mcp add polyrama --env POLYRAMA_API_TOKEN=<your-token> -- npx -y @polyrama/mcp
Codex
[mcp_servers.polyrama]
command = "npx"
args = ["-y", "@polyrama/mcp"]
[mcp_servers.polyrama.env]
POLYRAMA_API_TOKEN = "<your-token>"
Cursor, Windsurf, Cline, Goose, Zed, OpenClaw, and other stdio MCP clients use the same command and environment variable.
Tools
| Tool | Purpose | Scope |
|---|---|---|
polyrama_search_markets |
Search live Polymarket and Kalshi markets | read |
polyrama_get_market |
Inspect one market by token id | read |
polyrama_top_traders |
Rank public Polymarket wallets | read |
polyrama_get_trader |
Read one wallet's positions and performance | read |
polyrama_refresh_trader |
Refresh one public wallet | write:paper |
polyrama_recent_signals |
Read whales, jolts, spikes, and mispricing signals | read |
polyrama_list_bots |
List configured bots and status | read |
polyrama_state_snapshot |
Read the full dashboard state | read |
polyrama_run_backtest |
Run a historical strategy backtest | write:paper |
polyrama_place_paper_order |
Record a paper-only trade | write:paper |
The public MCP package has no live-order tool and never calls a live-order endpoint. It cannot move funds or submit an exchange order.
Environment variables
| Variable | Required | Default |
|---|---|---|
POLYRAMA_API_TOKEN |
Yes | — |
POLYRAMA_API_URL |
No | https://polyrama.io |
POLYRAMA_REQUEST_TIMEOUT_MS |
No | 30000 |
POLYRAMA_API_URL is intended for Polyrama development and staging deployments.
Development
npm ci
npm run check
npm pack --dry-run
See CONTRIBUTING.md before opening a pull request. Security reports should follow SECURITY.md.
Links
Disclaimer
Polyrama is for research and informational use only, not financial advice. Prediction markets involve risk. Review source data and venue rules before acting on any result.
License
MIT © 2026 Polyrama contributors
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。