The SolSentry MCP server provides Solana threat intelligence and rug pull risk analysis, enabling AI agents to assess wallet and token risk on Solana mainnet.
check_operator: Analyze a Solana wallet's history as a token deployer — returns confirmed rug count, risk label, behavioral tags, and a plain-English summary.
check_token: Evaluate a Solana token mint's risk profile — returns risk score, flags, operator history, and bundle detection to help decide whether to buy or list a token.
get_top_operators: Retrieve a ranked leaderboard of the worst serial rug pull deployers tracked by SolSentry (up to 50 operators), useful for blacklisting known bad actors.
get_network_stats: Fetch system-wide threat intelligence metrics including total scans, prediction accuracy, resolve rate, operator counts, and bot cluster data.
explain_risk: Get a plain-English explanation of why a specific wallet or token is considered risky — suitable for displaying warnings directly to end users.
The server continuously monitors Solana mainnet to track serial rug pull operators, bot clusters, and malicious token launches.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SolSentry MCP Check token 7GCihg... for rug risk"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RugCheck tells you a fire is burning. SolSentry tells you who lit it.
SolSentry packages its public operator-risk intelligence surface as an MCP
server, a TypeScript SDK, and a skills bundle. All interfaces use the live REST
API at https://api.solsentry.app.
Precision is auditable per-mint at /v1/predictions/{mint} (live). Pull any
current system numbers from the live API rather than this README — never cite a
hardcoded accuracy/precision figure or operator-level aggregate as a standing fact.
API stats: https://api.solsentry.app/v1/stats
NPM: https://www.npmjs.com/package/@solsentry/mcp
GitHub org: https://github.com/solsentry
Related MCP server: token-rugcheck
Surface | Use it when | Entry |
MCP server | AI agents (Claude Desktop, Cursor, Claude Code, any MCP client) |
|
TypeScript SDK | TS backends, bots, wallets, dApps that don't speak MCP |
|
Skills bundle | Claude Code / Cursor with the Agent Skills spec |
|
All three call the public REST API at api.solsentry.app. No API key
required for read endpoints.
Numbers drift daily as predictions resolve — verify live: curl https://api.solsentry.app/v1/stats
solsentry-mcp/
├── src/ ← TypeScript source (MCP server + SDK)
├── skills/
│ └── solsentry-postdeploy/ ← 1 skill, 6 references (progressive disclosure)
│ ├── SKILL.md orchestrator: when to load each reference
│ └── references/
│ ├── threat-intel.md · generic risk lookup
│ ├── counterparty.md · pre-CPI counterparty check
│ ├── monitor.md · post-deploy program monitoring
│ ├── forensics.md · post-incident drain trace
│ ├── token-launch.md · pre-launch readiness for your own token
│ └── cluster-graph.md · operator/bot network exploration
└── docs/ ← public reference docs
├── risk-scoring.md · scoring methodology + thresholds
├── flags.md · canonical flag glossary
├── openapi.yaml · machine-readable REST spec
└── x402-example.md · paid endpoint integration exampleSolSentry monitors Solana mainnet continuously and tracks serial rug pull operators, bot clusters, and malicious token launches. The data is refreshed every 30 seconds and available to any client that speaks MCP or plain HTTP.
npx -y @solsentry/mcp{
"mcpServers": {
"solsentry": {
"command": "npx",
"args": ["-y", "@solsentry/mcp"]
}
}
}{
"mcpServers": {
"solsentry": {
"command": "npx",
"args": ["-y", "@solsentry/mcp"]
}
}
}Tool | Purpose |
| Risk profile of a wallet as a token deployer |
| Risk profile of a token mint |
| System-wide public metrics |
| Plain-language summary for a wallet or mint |
import { SolSentryClient } from "@solsentry/mcp/client";
const client = new SolSentryClient();
const stats = await client.get("/v1/stats");
console.log(stats);curl https://api.solsentry.app/v1/stats
curl https://api.solsentry.app/v1/operator/<wallet-address>
curl https://api.solsentry.app/v1/predictions/<mint-address>Environment variable | Default | Purpose |
|
| API endpoint |
| — | Bearer token for authenticated endpoints |
Public quality claim: precision is auditable per-mint at /v1/predictions/{mint}
(live) — re-verify on the day; never ship a hardcoded precision number.
Node.js >= 18
MIT
Site: solsentry.app
X (project): @solsentryai
Telegram: t.me/solsentryai
GitHub: github.com/solsentry
Email: hello@solsentry.app
Built by: Crash Diniz · @crashdiniz
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
Solana pre-trade safety for AI agents: cabal, bundle, dump, deployer & honeypot in one verdict.
Rug-check & launch radar for trading agents: composite honeypot score, EVM+Solana, keyless x402.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/solsentry/solsentry-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server