Solana token rug-risk reports + tx explainer. Pay per call via x402 (USDC on Solana or Base).
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Solana SPL/Token-2022 rug-risk report: mint/freeze authority, risky Token-2022 extensions, top-holder concentration, DEX liquidity/volume/pool age, 0-100 risk score. Heuristic, not a guarantee. Costs 0.02 USDC per call via x402 (Solana or Base).
Solana token mint address
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http solana-rugcheck https://rugcheck.testbot-curt.workers.dev/mcp
Solana SPL/Token-2022 rug-risk report: mint/freeze authority, risky Token-2022 extensions, top-holder concentration, DEX liquidity/volume/pool age, 0-100 risk score. Heuristic, not a guarantee. Costs 0.02 USDC per call via x402 (Solana or Base).
| Argument | Type | Description |
|---|
| mint* | string | Solana token mint address |
{
"type": "object",
"required": [
"mint"
],
"properties": {
"mint": {
"type": "string",
"description": "Solana token mint address"
}
}
}Free sample rug-risk report (BONK) showing the output format of rug_check.
No arguments.
{
"type": "object",
"properties": {}
}Solana transaction explainer: status, fee, signers, programs invoked (named), and per-account SOL and token balance changes in plain JSON for any mainnet signature. Costs 0.01 USDC per call via x402 (Solana or Base).
| Argument | Type | Description |
|---|---|---|
| sig* | string | Solana transaction signature |
{
"type": "object",
"required": [
"sig"
],
"properties": {
"sig": {
"type": "string",
"description": "Solana transaction signature"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.