RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server
io.github.HOBSTER6615/rugradarHOBSTER6615streamable-httpv1.1.0Scanned
Solana-only rug checker: dev-wallet history, insider clusters, LP lock, honeypot test, x402 per call
9 tools: 1 do something that can't be undone, 4 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 0
- 1 finding
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.
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 RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server can do
The RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server is published by the GitHub account HOBSTER6615. It has 9 tools. It can do things that cannot be undone, such as sending, paying or publishing (verify_payment_and_get_key) and create or change data (4 tools: check_token, scan_link, watch_token and unwatch_token), but cannot delete data. 4 tools only read.
6 tools bring in text other people can write (check_token, scan_wallet, scan_link and 3 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.1.0.
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.
9 tools
Can't be undone 1Claude Code: ask
verify_payment_and_get_keyAfter paying a quote, verify the Solana transaction on-chain (correct recipient, amount worth at least 95% of the price, carries the quote reference, confirmed, under 7 days old) a…Reads text others writeNo findings
Why it is in this group
- The name "verify_payment_and_get_key" says "payment": a word that usually means money moves, which cannot be taken back.
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 After paying a quote, verify the Solana transaction on-chain (correct recipient, amount worth at least 95% of the price, carries the quote reference, confirmed, under 7 days old) and receive a RugRadar Pro API key valid for 30 days per payment. Idempotent: the same signature with the same order returns the same key; a signature can only be redeemed once.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 4Claude Code: ask
check_tokenCheck a Solana token for rug-pull and scam risk.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 Check a Solana token for rug-pull and scam risk. Input: a mint address, a pump fun or DexScreener link, or a $TICKER. Returns a 0-100 risk score (0-29 low risk, 30-59 caution, 60-100 high risk), plain-English red flags (mint/freeze authority, Token-2022 extensions, holder concentration, dev wallet and its launch history, linked insider wallets, LP lock, honeypot sell test, liquidity, drawdown) and a dump-model probability for tokens under 6 hours old. Read-only: never needs a wallet connection or signature. Free: 5 checks/day per IP (shared with the REST API); Pro key: unlimited. Automated risk signals, not financial advice. A low score is not a recommendation to buy.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
scan_linkScan a URL or pasted post text for wallet-drainer and phishing patterns (fake claim/airdrop pages, lookalike domains, wallet-connect bait).Reads text others write1 finding
Why it is in this group
- The name "scan_link" says "link": a word for a change.
- 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 "scan_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "scan_link" says "link": a word for a change.
Description, as the server wrote it Scan a URL or pasted post text for wallet-drainer and phishing patterns (fake claim/airdrop pages, lookalike domains, wallet-connect bait). Free: 20/day per IP; Pro: unlimited.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
unwatch_tokenPro: remove a token from this key's agent watchlist.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Pro: remove a token from this key's agent watchlist.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
watch_tokenPro: add a token to this key's agent watchlist (up to 25).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.
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 Pro: add a token to this key's agent watchlist (up to 25). RugRadar stores a baseline snapshot (score, liquidity, holder concentration, dev and insider holdings, sell test, authorities). Poll get_watch_status to see what changed. There are no push notifications over MCP; for push alerts use the Telegram bot.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 4Show 4 read-only tools
get_pro_quoteGet a payment quote for RugRadar Pro ($9 for 30 days, no auto-renewal): the exact USDC and SOL amounts, the Solana pay-to address, a unique reference to include in the payment (as …No findings
Why it is in this group
- The name "get_pro_quote" says "get": a word for reading.
Description, as the server wrote it Get a payment quote for RugRadar Pro ($9 for 30 days, no auto-renewal): the exact USDC and SOL amounts, the Solana pay-to address, a unique reference to include in the payment (as a Solana Pay reference key or in an SPL Memo), a signed order token, and x402 details when available. Does not move funds; the agent or its user must send the payment from their own wallet.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_pro_statusCheck whether a RugRadar Pro API key is valid and when it expires, plus the current free and Pro limits.No findings
Why it is in this group
- The name "get_pro_status" says "get": a word for reading.
Description, as the server wrote it Check whether a RugRadar Pro API key is valid and when it expires, plus the current free and Pro limits.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_watch_statusPro: re-check watched tokens (up to 5 stale ones per call; others use their last check) and report changes since each baseline: dev or insider wallets selling, liquidity pulled or …Reads text others writeNo findings
Why it is in this group
- The name "get_watch_status" says "get": a word for reading.
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 Pro: re-check watched tokens (up to 5 stale ones per call; others use their last check) and report changes since each baseline: dev or insider wallets selling, liquidity pulled or draining, holder concentration jumps, sell test failing, authorities re-enabled, risk score or dump-model spikes, price halving. Automated risk signals, not financial advice. A low score is not a recommendation to buy.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
scan_walletList the SPL tokens held by a PUBLIC Solana wallet address, riskiest first, with a quick risk score and top red flags per token.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
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 List the SPL tokens held by a PUBLIC Solana wallet address, riskiest first, with a quick risk score and top red flags per token. Never send a private key or seed phrase. Free: the 3 riskiest tokens, 5 scans/day per IP; Pro key: every token, unlimited. Automated risk signals, not financial advice. A low score is not a recommendation to buy.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
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 write6
- 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.
Looked at Nov 16, 2026, 14:19 UTC, unchanged since Nov 16, 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
- 5
- 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 5 tools that change things (1 irreversible, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://rugradar-bgcm.onrender.com/mcp: tools/list returned 9 tools to an anonymous client, including verify_payment_and_get_key (irreversible), check_token (write), scan_link (write), watch_token (write), unwatch_token (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnscan_link
The server marks "scan_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":true}; The name "scan_link" says "link": a word for a change.
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 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http rugradar https://rugradar-bgcm.onrender.com/mcpclaude mcp add --transport http rugradar https://rugradar-bgcm.onrender.com/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__rugradar__scan_wallet",
"mcp__rugradar__get_pro_quote",
"mcp__rugradar__get_pro_status",
"mcp__rugradar__get_watch_status"
],
"ask": [
"mcp__rugradar__check_token",
"mcp__rugradar__scan_link",
"mcp__rugradar__verify_payment_and_get_key",
"mcp__rugradar__watch_token",
"mcp__rugradar__unwatch_token"
],
"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 rugradar. Review it before you use it.
Capability tags behind 6 rules
- mcp__rugradar__check_token untrusted-input
- mcp__rugradar__scan_wallet untrusted-input
- mcp__rugradar__scan_link untrusted-input
- mcp__rugradar__verify_payment_and_get_key untrusted-input
- mcp__rugradar__watch_token untrusted-input
- mcp__rugradar__get_watch_status 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/io.github.HOBSTER6615/rugradar/verify?hash=f2c3bf855cbb2a58782f2d5a861f5ac79b4a04332d27010dcd66b70381924426" | jq -e '.changed == false'Pinned hash f2c3bf855cbb, from Nov 18, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.HOBSTER6615/rugradar/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.HOBSTER6615/rugradar)Source: MCP Registry · repository. Synced Nov 18, 2026, 02:17 UTC.
RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 5 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: verify_payment_and_get_key.
What tools does the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server have?
- 9 tools: 1 irreversible, 4 write, 4 read. verify_payment_and_get_key, check_token, scan_link, watch_token, unwatch_token, scan_wallet, get_pro_quote, get_pro_status and 1 more.
Does the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the RugRadar: Solana rug & scam checker (rugradar-bgcm) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.