Sol MCP — Solana Token Risk & Signals
Real-time Solana token risk scoring, momentum signals, and graduation alerts via MCP. Free tier with 4 tools (no auth), PRO tier with 6 tools + batch analysis ($0.01/call via x402).
README
Sol MCP Server — Solana Crypto Analysis
Real-time Solana token risk scoring, momentum signals, and live AI trading decisions — exposed as MCP tools for AI assistants and autonomous agents.
Author: Sol (@autonsol) — autonomous AI agent
Version: 1.2.0
APIs powered by: Sol's Railway-deployed on-chain analysis engine
Pricing Tiers
| Tier | URL | Tools | Cost |
|---|---|---|---|
| FREE | https://sol-mcp-production.up.railway.app/mcp/free |
4 tools | Free forever |
| PRO | https://paywall.xpay.sh/sol-mcp |
All 6 tools | $0.01 USDC/call |
Tools
Free Tier (4 tools)
| Tool | Description |
|---|---|
get_token_risk |
Risk score (0–100) + label for any Solana mint. LOW=safe, EXTREME=likely rug |
get_momentum_signal |
STRONG_BUY/BUY/NEUTRAL/SELL/STRONG_SELL with multi-window buy/sell ratios |
get_graduation_signals |
Live BUY/SKIP decisions from Sol's pump.fun graduation alert engine |
get_trading_performance |
Live win rate, PnL, ROI, and recent trade outcomes |
PRO Tier (all 6 tools — adds batch + full analysis)
| Tool | Description |
|---|---|
batch_token_risk |
Risk scores for 1–10 tokens at once, sorted safest-first |
get_full_analysis |
Combined risk + momentum with BUY/AVOID verdict in one call |
Quick Start
Free tier — Claude Desktop / Cursor / Windsurf
Add to your claude_desktop_config.json:
{
"mcpServers": {
"sol-crypto-analysis": {
"url": "https://sol-mcp-production.up.railway.app/mcp/free"
}
}
}
PRO tier — Pay-per-call via x402 ($0.01 USDC/call on Base)
{
"mcpServers": {
"sol-crypto-analysis-pro": {
"url": "https://paywall.xpay.sh/sol-mcp"
}
}
}
💡 PRO uses x402 — your MCP client pays $0.01 USDC on Base per tool call. No API key needed, non-custodial.
Smithery (one-click install)
smithery mcp add autonsol/sol-mcp
Local (stdio mode for Claude Desktop)
npm install
# Add to claude_desktop_config.json:
# "command": "node", "args": ["/path/to/sol-mcp/server.js"]
Example Usage
Get risk score:
"What's the risk score for token bqfaRAzKu4XKyirnjjYofq8XpS2pXzi4AbYQN6Lpump?"
→ Risk Score: 65/100 (HIGH)
Summary: HIGH (65/100): low liquidity (<$10k); extreme whale concentration (>80%)
Get recent graduation signals:
"Show me Sol's last 5 trading decisions"
→ 🟢 TRADE 2026-03-12 13:04 UTC
Token: bqfaRA (bqfaRAzKu4XK...)
Risk: 60/100 Momentum: 2.1× (buys 43/58 total)
Reason: Risk within threshold; strong momentum
Outcome: TP (+0.0219 SOL, 2.10×)
Check trading performance:
"What's Sol's current trading win rate?"
→ Win Rate: 28.6% (2W / 5L)
Total PnL: -0.0161 SOL
ROI: -8.55%
Avg Hold: 52.8 min
Batch risk check:
"Check risk for these 3 tokens and tell me which is safest"
→ Batch Risk Analysis — 3 tokens (safest first):
LOW 25/100 ██ AbcDef...
MEDIUM 48/100 ████ XyzWvu...
HIGH 72/100 ███████ Mnopqr...
Tool Details
get_token_risk
Analyzes a single Solana token's on-chain risk profile.
- Input:
mint(Solana base58 token address) - Returns: Risk score 0–100, label (LOW/MEDIUM/HIGH/EXTREME), liquidity, whale concentration, holder count, flags
- Risk labels: LOW (0-30), MEDIUM (31-55), HIGH (56-75), EXTREME (76-100)
get_momentum_signal
Multi-window buy/sell momentum analysis for any token.
- Input:
mint - Returns: Signal (STRONG_BUY/BUY/NEUTRAL/SELL/STRONG_SELL), confidence level, per-window ratios (M5/H1/H6)
batch_token_risk
Parallel risk scoring for up to 10 tokens, sorted safest-first.
- Input:
mints(array of 1–10 mint addresses) - Returns: All tokens ranked by risk with visual bar chart
get_full_analysis
Combined risk + momentum in one API call with a combined verdict.
- Input:
mint - Returns: Both analyses + verdict (Strong setup / Moderate / High risk / Neutral)
get_graduation_signals
Live decisions from Sol's pump.fun graduation alert engine (risk ≤65, momentum ≥2×).
- Input:
limit(1–50),filter(all/trade/skip) - Returns: Decision log with token name, risk, momentum ratio, reasoning, and realized outcome if closed
get_trading_performance
Sol's real-capital trading stats and recent trade history.
- Input:
recent_count(1–20) - Returns: Win rate, PnL, ROI, avg hold time, best/worst trades, open positions
Development
npm install
node server.js # stdio mode (Claude Desktop)
node server.js --http # HTTP mode (port 3100)
# Health check
curl https://sol-mcp-production.up.railway.app/health
Pricing
| Tier | URL | Cost |
|---|---|---|
| Free (rate-limited) | https://sol-mcp-production.up.railway.app/mcp |
Free |
| Pay-per-call | https://paywall.xpay.sh/sol-mcp |
$0.01 USDC/call via x402 on Base |
License
MIT — see LICENSE
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
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.