Read-only Solana SPL/Token-2022 rug-risk check: 0-100 score (higher=riskier) with reasons.
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.
Batch Solana token risk check (PAID, x402 over REST): up to 20 mints in one call for one flat price. This tool returns exact x402 payment instructions for POST /v1/paid/batch-check.
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 haris-guardian https://haris-api.vercel.app/mcp
Batch Solana token risk check (PAID, x402 over REST): up to 20 mints in one call for one flat price. This tool returns exact x402 payment instructions for POST /v1/paid/batch-check.
| Argument | Type | Description |
|---|---|---|
| mints* | array |
{
"type": "object",
"title": "batch_check_solana_tokensArguments",
"required": [
"mints"
],
"properties": {
"mints": {
"type": "array",
"items": {
"type": "string"
},
"title": "Mints"
}
}
}Scam/rug risk check for a Solana SPL or Token-2022 token mint. Returns a 0-100 risk score (HIGHER = RISKIER), a verdict, and flags with plain-English reasons: mint/freeze authority, permanent delegate, transfer hooks/fees, holder concentration, liquidity, LP burn/lock %, Streamflow locks and a simulated buy+sell (honeypot test). Read-only; never signs or trades.
| Argument | Type | Description |
|---|---|---|
| mint* | string |
{
"type": "object",
"title": "check_solana_tokenArguments",
"required": [
"mint"
],
"properties": {
"mint": {
"type": "string",
"title": "Mint"
}
}
}Deep Solana token risk check (PAID, x402 over REST): holder concentration (top1/top5/top10 % of supply), top wallets linked by a shared funder (bundles/insiders), creator-funded holders, fresh wallets, LP lock/burn status, authorities, score + reasons. This tool returns exact x402 payment instructions for POST /v1/paid/deep-check; pay with any x402 client.
| Argument | Type | Description |
|---|---|---|
| mint* | string |
{
"type": "object",
"title": "deep_check_solana_tokenArguments",
"required": [
"mint"
],
"properties": {
"mint": {
"type": "string",
"title": "Mint"
}
}
}Watch/diff a Solana token: pass the mint and a previous Haris result (from check_solana_token or an earlier diff); returns alerts on what changed (authority re-enabled, LP unlocked, liquidity pulled, sell blocked, new red flags) plus the fresh result. Shares the free tier with check_solana_token; then x402 via POST /v1/paid/diff.
| Argument | Type | Description |
|---|---|---|
| mint* | string | |
| previous* | object |
{
"type": "object",
"title": "diff_solana_tokenArguments",
"required": [
"mint",
"previous"
],
"properties": {
"mint": {
"type": "string",
"title": "Mint"
},
"previous": {
"type": "object",
"title": "Previous",
"additionalProperties": true
}
}
}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 4, 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.