RugShield MCP server
io.github.raphaelbgr/rugshieldraphaelbgrstreamable-httpv0.1.3Scanned
Solana checks and free panel quote via MCP; paid parallel advisor panel via HTTP. USDC x402.
5 tools: 4 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- 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 RugShield MCP server can do
The RugShield MCP server is published by the GitHub account raphaelbgr. It has 5 tools. It can create or change data (4 tools: check_solana_transaction, check_solana_token_risk, quote_solana_risk_panel and retry_failed_job), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 21, 2026, version 0.1.3.
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.
5 tools
Changes things 4Claude Code: ask
check_solana_token_riskUse before buying a pump.fun token when you have its Solana mint address.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 Use before buying a pump.fun token when you have its Solana mint address. Returns advisory flags evaluated on selected historical tokens; no flags does not mean safe. Optional idempotency_key is random 32-byte base64url. A signed call waits up to 20 seconds for analysis and can settle without a key. If still processing, echo the unpaid job_id with the same proof and mint when ready. get_job_result reports processing and retry_after_s for free; the result appears there only after settlement. Costs $0.01 USDC via x402.
check_solana_transactionUse before signing an unsigned Solana transaction, not for a token mint alone.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 Use before signing an unsigned Solana transaction, not for a token mint alone. Provide a real unsigned Solana transaction serialized as base64, with optional signer and expected intent. Malformed input is rejected before payment. Simulation returns ALLOW, WARN or BLOCK with reasons and balance changes. Optional idempotency_key is random 32-byte base64url. A signed call waits up to 20 seconds for analysis and can settle without a key. If still processing, echo the unpaid job_id with the same proof and arguments when ready. get_job_result reports processing and retry_after_s for free; the result appears there only after settlement. Costs $0.01 USDC via x402.
quote_solana_risk_panelFree quote for the paid HTTP panel of parallel Solana risk advisors.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 Free quote for the paid HTTP panel of parallel Solana risk advisors. Pass a Solana mint and optionally comma-separated public advisor aliases from GET /v1/advisors and a CAIP-2 token chain. Returns a canonical HTTP URL and estimated total in USDC; does not call or pay advisors. The URL's HTTP 402 payment quote is authoritative. Request it without a proof, then prepay the exact original URL with a compatible x402 HTTP client. A confirmed prepayment returns 202 with job_id/status_url: poll status_url for free; no second signed request or payment is needed. Failed paid panels require support review; there is no automatic refund.
retry_failed_jobRetry a failed paid job for free.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 Retry a failed paid job for free. Transaction and token checks each have one manual retry per job ID; if it still fails, keep the job ID and contact rugshield@fastsoftware.uk for review. There is no automatic refund.
Only reads 1Show 1 read-only tool
get_job_resultPoll an accepted job for free.No findings
Why it is in this group
- The name "get_job_result" says "get": a word for reading.
Description, as the server wrote it Poll an accepted job for free. A paid job reports processing, ready, or failed without revealing its result before settlement; retry_after_s gives the next polling delay, capped at two minutes. An uncertain payment reports needs_review with no automatic retry: keep the job ID and contact support without another payment. After confirmed settlement, retrieve the saved result. Read agent_guidance.payment and agent_guidance.analysis separately. Legacy charged:null means unconfirmed, not free. Historical saved replies remain unchanged; this free status tool exposes current state explanations.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 20, 2026, 19:10 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://getrugshield.com/mcp/: tools/list returned 5 tools to an anonymous client, including check_solana_transaction (write), check_solana_token_risk (write), quote_solana_risk_panel (write), retry_failed_job (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:get_job_resultOnly readsdescription
- Changed:quote_solana_risk_panelChanges thingsdescription
Install
Pinned to version 0.1.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http rugshield https://getrugshield.com/mcp/claude mcp add --transport http rugshield https://getrugshield.com/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.
{
"permissions": {
"allow": [
"mcp__rugshield__get_job_result"
],
"ask": [
"mcp__rugshield__check_solana_transaction",
"mcp__rugshield__check_solana_token_risk",
"mcp__rugshield__quote_solana_risk_panel",
"mcp__rugshield__retry_failed_job"
],
"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 rugshield. Review it before you use it.
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.raphaelbgr/rugshield/verify?hash=f635103ea7accb14706fbb26683cb3b4b72d7ef5e1d7e9551351e300ec672b92" | jq -e '.changed == false'Pinned hash f635103ea7ac, from Nov 21, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.raphaelbgr/rugshield/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.raphaelbgr/rugshield)Source: MCP Registry. Synced Oct 21, 2026, 18:45 UTC.
RugShield MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the RugShield MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 4 of which can change, send or delete something, and 0 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 RugShield MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the RugShield MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the RugShield MCP server have?
- 5 tools: 4 write, 1 read. check_solana_transaction, check_solana_token_risk, quote_solana_risk_panel, retry_failed_job and get_job_result.
Does the RugShield MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the RugShield MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the RugShield MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 6, 2026. Every change is on this page and in its Atom feed.