Haris Guardian - Solana Token Risk Check MCP server
io.github.fitness9991/haris-guardianfitness9991streamable-httpv1.0.1Scanned
Read-only Solana SPL/Token-2022 rug-risk check: 0-100 score (higher=riskier) with reasons.
7 tools: 5 change things and 2 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
5 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 Haris Guardian - Solana Token Risk Check MCP server can do
The Haris Guardian - Solana Token Risk Check MCP server is published by the GitHub account fitness9991. It has 7 tools. It can create or change data (5 tools: check_solana_token, deep_check_solana_token, batch_check_solana_tokens, plan_haris_burn and 1 more), but cannot delete data. 2 tools only read.
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 18, 2026, version 1.0.1.
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.
7 tools
Changes things 5Claude Code: ask
batch_check_solana_tokensBatch Solana token risk check (PAID, x402 over REST): up to 20 mints in one call for one flat price.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 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.
check_solana_tokenScam/rug risk check for a Solana SPL or Token-2022 token mint.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 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.
claim_haris_burnSubmit a confirmed $HARIS Burn Game transaction signature.No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit a confirmed $HARIS Burn Game transaction signature. Verifies the on-chain burn, credits the 1:1 return, and sends the same amount back immediately from the Round 1 wallet when instant returns are on. Idempotent per signature. Haris never signs.
deep_check_solana_tokenDeep 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 ho…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 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.
plan_haris_burnBuild an unsigned $HARIS Burn Game transaction for a given Solana wallet and amount (max 10,000 HARIS, memo haris-burn-round-1).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 Build an unsigned $HARIS Burn Game transaction for a given Solana wallet and amount (max 10,000 HARIS, memo haris-burn-round-1). Returns a base64 unsigned tx for the wallet owner to sign. Haris never signs or holds keys. Not a payout.
Only reads 2Show 2 read-only tools
diff_solana_tokenWatch/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…No findings
Why it is in this group
- The name "diff_solana_token" says "diff": a word for reading.
Description, as the server wrote it 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.
get_haris_burn_gameFree $HARIS Burn Game (Round 1) stats: total burned, remaining 100,000,000 capacity, round status, returnsStatus (instant 1:1 returns when live), and the top-20 leaderboard (wallet…No findings
Why it is in this group
- The name "get_haris_burn_game" says "get": a word for reading.
Description, as the server wrote it Free $HARIS Burn Game (Round 1) stats: total burned, remaining 100,000,000 capacity, round status, returnsStatus (instant 1:1 returns when live), and the top-20 leaderboard (wallet, total burned, number of burns). Read-only. Never signs. The same amount is returned instantly and automatically from the Round 1 wallet when instant returns are on.
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 19, 2026, 17:23 UTC, unchanged since Nov 12, 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://haris-api.vercel.app/mcp: tools/list returned 7 tools to an anonymous client, including check_solana_token (write), deep_check_solana_token (write), batch_check_solana_tokens (write), plan_haris_burn (write), claim_haris_burn (write)
Posture changes
- Nov 12, 2026
- Tools that change things, listed without credentials: 3 to 5
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.
Tools3 added.+3 addedView diff
- Added:claim_haris_burnChanges things
- Added:get_haris_burn_gameOnly reads
- Added:plan_haris_burnChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 5.View diff
- Tools that change things, listed without credentials: 3 to 5
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http haris-guardian https://haris-api.vercel.app/mcpclaude mcp add --transport http haris-guardian https://haris-api.vercel.app/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__haris-guardian__diff_solana_token",
"mcp__haris-guardian__get_haris_burn_game"
],
"ask": [
"mcp__haris-guardian__check_solana_token",
"mcp__haris-guardian__deep_check_solana_token",
"mcp__haris-guardian__batch_check_solana_tokens",
"mcp__haris-guardian__plan_haris_burn",
"mcp__haris-guardian__claim_haris_burn"
],
"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 haris-guardian. 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.fitness9991/haris-guardian/verify?hash=c25424dd86f95bdc2d9445fc4432124dc9b116fcfd39dcb4267b833f38ed1bda" | jq -e '.changed == false'Pinned hash c25424dd86f9, from Nov 18, 2026, 06:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.fitness9991/haris-guardian/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.fitness9991/haris-guardian)Source: MCP Registry · repository. Synced Nov 4, 2026, 12:17 UTC.
Haris Guardian - Solana Token Risk Check MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Haris Guardian - Solana Token Risk Check MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 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 Haris Guardian - Solana Token Risk Check MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Haris Guardian - Solana Token Risk Check 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 Haris Guardian - Solana Token Risk Check MCP server have?
- 7 tools: 5 write, 2 read. check_solana_token, deep_check_solana_token, batch_check_solana_tokens, plan_haris_burn, claim_haris_burn, diff_solana_token and get_haris_burn_game.
Does the Haris Guardian - Solana Token Risk Check MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Haris Guardian - Solana Token Risk Check MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Haris Guardian - Solana Token Risk Check MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.