Skip to content

solsnap MCP server

art.maddegen.agent/solsnapagent.maddegen.artstreamable-httpv1.0.0Scanned

Solana token/wallet rug-risk scoring. Free scan; $2 SOL unlocks full wallet report. No signup.

4 tools: 1 do something that can't be undone and 3 change things.

Tools: 0 delete, 1 irreversible, 3 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the solsnap MCP server can do

The solsnap MCP server is published by agent.maddegen.art, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (wallet_sweep_pay) and create or change data (3 tools: solsnap_scan, wallet_sweep and wallet_sweep_report), but cannot delete data. None of its tools only reads.

4 tools bring in text other people can write (solsnap_scan, wallet_sweep, wallet_sweep_pay and 1 more).

The fixed checks matched 2 findings (base64-blob and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 10, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

4 tools

Can't be undone 1Claude Code: ask
  • wallet_sweep_payOptional helper: returns only the SOL amount and address that unlock the full wallet_sweep report for one wallet (the same details wallet_sweep already includes when unpaid).Reads text others write1 finding

    Why it is in this group

    • The name "wallet_sweep_pay" says "pay": a word that usually means money moves, which cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "wallet_sweep_pay" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "wallet_sweep_pay" says "pay": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Optional helper: returns only the SOL amount and address that unlock the full wallet_sweep report for one wallet (the same details wallet_sweep already includes when unpaid). Send the exact amount; then call wallet_sweep again. Errors (isError=true): malformed address.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Get payment details for a full sweep
Changes things 3Claude Code: ask
  • solsnap_scanGrade one Solana token mint for rug risk: 0-100 safety score, A-F grade and itemised flags.Reads text others write1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The input schema at properties.mint.description contains a 44-character base64 string.

      Matched text

      inputSchema.properties.mint.description: "...32-44 chars), e.g. DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263 (BONK). Not a walle..."

      What this check looks for
    Description, as the server wrote it
    Grade one Solana token mint for rug risk: 0-100 safety score, A-F grade and itemised flags. Free. Checks mint/freeze authority, Token-2022 traps (transfer fee, hook, permanent delegate, pause), mutable metadata, pump.fun curve status, top-holder concentration (wallets vs pools), liquidity, pair age, FDV/liquidity, volume/liquidity, buy/sell imbalance. Does NOT check LP locks. Use it before buying one token; to grade everything a wallet holds use wallet_sweep instead. Unknown or unlisted mints still return on-chain checks with found=false. Errors (isError=true): malformed mint. Live data from Solana RPC + DexScreener, typically 1-4 s.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Solana token rug-risk scan
  • wallet_sweepGrade every token a Solana wallet holds for rug risk in one call (up to 40 holdings).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Grade every token a Solana wallet holds for rug risk in one call (up to 40 holdings). Free: totals plus the 3 riskiest holdings. Paid ($1 in SOL, one time per wallet): every holding itemised. This one tool covers the whole paid flow: an unpaid result includes payment.pay_to and payment.amount_sol; send exactly that amount (the amount identifies the wallet), then call wallet_sweep again with the same address and it returns status=full once the payment is seen on chain (usually within 30 s). Use solsnap_scan for a single token. Errors (isError=true): malformed address. Empty wallets return tokens_held=0.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Solana wallet rug-risk sweep
  • wallet_sweep_reportLegacy alias of wallet_sweep kept for older clients: returns status=full with every holding once the wallet's payment has settled, otherwise status=not_paid with payment details.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Legacy alias of wallet_sweep kept for older clients: returns status=full with every holding once the wallet's payment has settled, otherwise status=not_paid with payment details. Prefer wallet_sweep. Errors (isError=true): malformed address.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Fetch a paid sweep report

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:30 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agent.maddegen.art/mcp: tools/list returned 4 tools to an anonymous client, including wallet_sweep_pay (irreversible), solsnap_scan (write), wallet_sweep (write), wallet_sweep_report (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The input schema at properties.mint.description contains a 44-character base64 string.

    Matched text

    inputSchema.properties.mint.description: "...32-44 chars), e.g. DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263 (BONK). Not a walle..."

    What this check looks for
  • The server marks "wallet_sweep_pay" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "wallet_sweep_pay" says "pay": a word that usually means money moves, which cannot be taken back.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http solsnap https://agent.maddegen.art/mcp
claude mcp add --transport http solsnap https://agent.maddegen.art/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__solsnap__solsnap_scan",
      "mcp__solsnap__wallet_sweep",
      "mcp__solsnap__wallet_sweep_pay",
      "mcp__solsnap__wallet_sweep_report"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as solsnap. Review it before you use it.

Capability tags behind 4 rules
  • mcp__solsnap__solsnap_scan untrusted-input
  • mcp__solsnap__wallet_sweep untrusted-input
  • mcp__solsnap__wallet_sweep_pay untrusted-input
  • mcp__solsnap__wallet_sweep_report untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/art.maddegen.agent/solsnap/verify?hash=e47c33eaaf1466991cf312ea8316ab6f81c0d503792e0113e41ec106f53a864f" | jq -e '.changed == false'

Pinned hash e47c33eaaf14, from Nov 10, 2026, 07:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/art.maddegen.agent/solsnap/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for art.maddegen.agent/solsnap
[![Anlyon Radar](https://radar.anlyon.com/badge/art.maddegen.agent/solsnap.svg)](https://radar.anlyon.com/servers/art.maddegen.agent/solsnap)

Source: MCP Registry · repository. Synced Oct 21, 2026, 17:45 UTC.

solsnap MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the solsnap MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 4 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the solsnap MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the solsnap MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: wallet_sweep_pay.

What tools does the solsnap MCP server have?

4 tools: 1 irreversible, 3 write. wallet_sweep_pay, solsnap_scan, wallet_sweep and wallet_sweep_report.

Does the solsnap MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the solsnap MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the solsnap MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.