Skip to main content
Glama

NodusAI MCP Server

NodusAI MCP Server

AI-Powered Signals for Prediction Markets — accessible to any AI agent via MCP.

AI agents connect to this server to get Oracle signals for Polymarket and Kalshi prediction markets. Signals are generated by Gemini 2.5 Flash with real-time web grounding.


How it works

Agent → nodusai.app → connect wallet → pay $1 USDC → get session token
                                                              ↓
Agent → MCP Server (nodus_get_signal) → nodusai.app/api/prediction → signal
  1. Visit nodusai.app and connect your wallet

  2. Paste a Polymarket or Kalshi market URL

  3. (Optional) Add your desired outcome (YES / NO)

  4. Pay $1 USDC — confirmed on-chain

  5. Get a session token good for 3 queries

  6. Use the session token with nodus_get_signal in any MCP client


Related MCP server: telekash-mcp-server

Payment model

  • Cost: $1 USDC = 3 Oracle signal queries

  • Networks: Base, Ethereum, Avalanche (any EVM chain)

  • Token: USDC

  • Non-custodial: payments go directly on-chain via nodusai.app

  • Session: one payment = one session token = 3 queries (24h validity)


Available tools

Tool

Description

nodus_pricing

View pricing and how to get a session token

nodus_get_signal

Get an Oracle signal using your session token

nodus_verify_signal

Audit grounding sources of a past signal

nodus_query_history

Your recent query history

nodus_admin_stats

Platform-wide stats (admin)

nodus_admin_queries

Full query registry dump (admin)


Signal format

Every Oracle response follows NodusAI's structured schema:

{
  "market_name": "Will the Fed cut rates in June 2026?",
  "predicted_outcome": "YES",
  "probability": 0.73,
  "confidence_score": "HIGH",
  "key_reasoning": "Recent FOMC minutes and inflation data suggest...",
  "grounding_sources": [
    { "title": "Reuters: Fed signals rate path", "url": "https://..." },
    { "title": "AP: CPI data June 2026", "url": "https://..." }
  ]
}

Deploy in 5 minutes

  1. Fork this repo on GitHub

  2. Go to railway.app → New Project → Deploy from GitHub repo

  3. Select your fork

  4. Add environment variable: NODUSAI_API_BASE = https://nodusai.app

  5. Railway auto-detects railway.json and deploys

  6. Copy your Railway URL


Option 2 — Render (free tier)

  1. Fork this repo

  2. Go to render.com → New Web Service → connect your fork

  3. Set Build command: npm install and Start command: node src/server-http.js

  4. Add env var: NODUSAI_API_BASE=https://nodusai.app


Option 3 — Fly.io

fly launch --name nodusai-mcp
fly secrets set NODUSAI_API_BASE=https://nodusai.app
fly deploy

Connect AI agents

Claude Desktop

File: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "nodusai": {
      "url": "https://nodusai-mcp-production.up.railway.app/sse"
    }
  }
}

Cursor

File: ~/.cursor/mcp.json

{
  "mcpServers": {
    "nodusai": {
      "url": "https://nodusai-mcp-production.up.railway.app/sse",
      "transport": "sse"
    }
  }
}

Windsurf

File: ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "nodusai": {
      "serverUrl": "https://nodusai-mcp-production.up.railway.app/sse"
    }
  }
}

Claude Code (CLI)

claude mcp add --transport sse nodusai https://nodusai-mcp-production.up.railway.app/sse

Custom JS agent

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse.js";

const client = new Client({ name: "my-agent", version: "1.0.0" }, { capabilities: {} });
await client.connect(new SSEClientTransport(new URL("https://nodusai-mcp-production.up.railway.app/sse")));

// Step 1 — get a session token at https://nodusai.app ($1 USDC)

// Step 2 — query the Oracle
const result = await client.callTool({
  name: "nodus_get_signal",
  arguments: {
    marketUrl:      "https://polymarket.com/event/...",
    sessionToken:   "your-session-token-from-nodusai.app",
    desiredOutcome: "YES", // optional
  }
});

Custom Python agent

from mcp.client.sse import sse_client
from mcp import ClientSession

async with sse_client("https://nodusai-mcp-production.up.railway.app/sse") as (read, write):
    async with ClientSession(read, write) as session:
        await session.initialize()

        # Get a session token at https://nodusai.app first ($1 USDC)
        result = await session.call_tool("nodus_get_signal", {
            "marketUrl":      "https://kalshi.com/markets/...",
            "sessionToken":   "your-session-token-from-nodusai.app",
            "desiredOutcome": "YES",  # optional
        })

Local development

git clone https://github.com/NodusAI-Your-Prediction-Broker/nodusai-mcp
cd nodusai-mcp
npm install

# Dev mode (mock oracle — no real API calls needed)
npm run dev:http

Test with:

curl http://localhost:3000/health
curl http://localhost:3000/info

Available Tools

6 tools
nodus_admin_queriesC

[ADMIN] Full query registry dump.

Inputs: limit.

nodus_admin_statsA

[ADMIN] Platform stats: total queries, breakdown by platform.

Inputs: no named parameters.

nodus_get_signalA

Get an Oracle signal for a Polymarket or Kalshi prediction market. Requires a session token from nodusai.app ($1 USDC = 3 queries). Optionally pass a desiredOutcome (YES/NO) to focus the analysis. Returns probability, confidence, reasoning, and grounding sources.

Inputs: marketUrl (required), sessionToken (required), desiredOutcome, walletAddress, +1 more.

nodus_pricingA

View NodusAI pricing and how to get started. Pay $1 USDC on nodusai.app → get a session token → use it for 3 Oracle signal queries.

Inputs: no named parameters.

nodus_query_historyC

View your recent NodusAI oracle query history.

Inputs: walletAddress (required), limit.

nodus_verify_signalA

Retrieve grounding sources for a past signal to verify the Oracle's reasoning.

Inputs: queryId (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 6 tools

    Disambiguation4/5

    Most tools have distinct purposes: admin queries vs. admin stats, get_signal vs. verify_signal, pricing vs. query history. However, 'nodus_admin_queries' and 'nodus_admin_stats' could be slightly confused as both provide administrative data, though their specific focuses differ.

    Naming Consistency5/5

    All tool names follow a consistent 'nodus_' prefix with descriptive suffixes in snake_case, such as 'nodus_admin_queries', 'nodus_get_signal', and 'nodus_verify_signal'. This pattern is uniform across all six tools, making them predictable and easy to identify.

    Tool Count5/5

    With 6 tools, the server is well-scoped for its purpose of providing Oracle signals and related administrative and historical functions. Each tool serves a clear role without unnecessary bloat, covering core operations like signal retrieval, verification, pricing, and history.

    Completeness4/5

    The tool set covers key aspects: signal retrieval, verification, pricing, query history, and admin functions. A minor gap is the lack of a tool for managing session tokens or handling payments directly, but agents can work around this using the provided pricing and signal tools.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

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

    • Pay-per-call ($0.005-$0.03 USDC) market, on-chain, and prediction-market data API for AI agents and trading bots via x402 — no signup, no API key. Remote MCP server, 28 tools: token security (honeypot/liquidity/counterfeit checks), Hyperliquid oracle-gap risk, kimchi premium, funding APR, DEX slippage, Polymarket arbitrage/liquidity audits, Hyperliquid HIP-4 odds.

    • Your agent needs the crowd's number — live odds on elections, policy, macro prints and sport, from the venues where people put money behind the opinion. **What you can ask for** • "What are the current odds on this event?" • "List the open markets on this topic across both venues." • "Show recent trades and how the price moved." • "What is the implied probability now versus a week ago?" **How to use it** Point any MCP client at https://mcp.aisa.one/prediction-market-data/mcp and sign in with OAuth — there is no key to create or paste. 5 tools: Kalshi markets and trades, Polymarket markets, events and activity. **Why this rather than the source** Both venues in one shape, so the same question can be priced twice. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Read the odds here, then ask the same agent for the market data or the news behind them — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/finance/mcp for equities, crypto and prediction markets in one place.

    • Pay-per-call DeFi and macro intel for AI agents. x402 USDC tools via streamable HTTP /api/mcp.

      https://conc-exe.xyz/api/mcp

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Real-time prediction market intelligence for AI agents. Query Polymarket and Kalshi markets, wallet profiles, smart money leaderboards, social pulse signals, price candlesticks, and orderbook data — 13 agents, one MCP connection. Powered by 1.1TB+ of historical data.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Prediction market probability oracle for AI agents. 26 tools across 500+ live markets from Kalshi and Polymarket. Cross-source arbitrage detection, structured TPF signals, Kelly Criterion sizing, agent performance tracking, and webhook alerts.
      9
      83 npm
      1
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A monetizable remote MCP server that provides prediction-market intelligence tools for AI agents, enabling discovery, evaluation, and mispricing detection across venues like Polymarket and Kalshi with per-call payment.
      1
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Prediction market intelligence for AI agents, enabling real-time access to whale trades, market data, signals, and AI-synthesized analysis from Kalshi and Polymarket via a standardized protocol.
      -