Trust Check MCP server
io.github.gmahar82-stack/trust-checkgmahar82-stackstreamable-httpv1.1.0Scanned
Base crypto safety for agents: honeypot/tax test, address poisoning, rug feed, creator record.
5 tools: 5 change things.
- Reads private data · 0
- Reads text others write · 5
- 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 Trust Check MCP server can do
The Trust Check MCP server is published by the GitHub account gmahar82-stack. It has 5 tools. It can create or change data (5 tools: check_token_safety, check_address_safety, recent_liquidity_collapses, check_token_creator and 1 more), but cannot delete data. None of its tools only reads.
5 tools bring in text other people can write (check_token_safety, check_address_safety, recent_liquidity_collapses and 2 more).
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 20, 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.
5 tools
Changes things 5Claude Code: ask
check_address_safetyBefore sending crypto on Base, check the destination: scam blacklists, address poisoning (a look-alike of an address you really use; pass `from` = your wallet), token contracts and…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 Before sending crypto on Base, check the destination: scam blacklists, address poisoning (a look-alike of an address you really use; pass `from` = your wallet), token contracts and burn addresses where funds are lost, never-used addresses. Returns a verdict with reasons. 5 free checks per day, then $0.002 per check via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_token_creatorBefore buying a newly launched Base token, check the wallet that deployed it: how many of its earlier tokens Rug Watch followed, and how many collapsed (rug pull or dump).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 Before buying a newly launched Base token, check the wallet that deployed it: how many of its earlier tokens Rug Watch followed, and how many collapsed (rug pull or dump). Verdict: serial_collapser / collapsed_before / no_collapses_seen / unknown. 5 free calls per day, then $0.002 per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
check_token_safetyBefore buying a token on Base, check it: simulates a real buy and sell (honeypot and hidden-tax test), reads owner powers (mint, blacklist, fee changes, pause), whale concentration…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 Before buying a token on Base, check it: simulates a real buy and sell (honeypot and hidden-tax test), reads owner powers (mint, blacklist, fee changes, pause), whale concentration, liquidity lock and scam lists. Returns a verdict (scam / high_risk / caution / low_risk) with plain-language reasons. 5 free checks per day, then $0.002 per check via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
deep_token_safety_reportFull due diligence before a bigger buy of a Base token: the token check (buy/sell simulation, taxes, owner powers, whales, liquidity, scam lists) plus the creator's Rug Watch recor…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 Full due diligence before a bigger buy of a Base token: the token check (buy/sell simulation, taxes, owner powers, whales, liquidity, scam lists) plus the creator's Rug Watch record, wallet check and first funder, the owner wallet, the token's liquidity history, website domain age, how often new Base tokens collapse, an AI summary and a what-to-do list. $0.10 per report via x402 (USDC on Base), no free calls; failures are not charged.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
recent_liquidity_collapsesNew Base tokens whose pool liquidity collapsed (fell 90%+ from its peak: a rug pull or a heavy dump) in the last hours, newest first, with peak and remaining liquidity, hours from …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 New Base tokens whose pool liquidity collapsed (fell 90%+ from its peak: a rug pull or a heavy dump) in the last hours, newest first, with peak and remaining liquidity, hours from launch and the creator wallet. Use it to exit positions and blocklist serial creators. 5 free calls per day, then $0.002 per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- 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 write5
- 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, 19:05 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
- 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://trust-check.gm-tools.workers.dev/mcp: tools/list returned 5 tools to an anonymous client, including check_token_safety (write), check_address_safety (write), recent_liquidity_collapses (write), check_token_creator (write), deep_token_safety_report (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.
Tools1 changed.~1 changedView diff
- Changed:deep_token_safety_reportChanges thingsdescription
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http trust-check https://trust-check.gm-tools.workers.dev/mcpclaude mcp add --transport http trust-check https://trust-check.gm-tools.workers.dev/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": [],
"ask": [
"mcp__trust-check__check_token_safety",
"mcp__trust-check__check_address_safety",
"mcp__trust-check__recent_liquidity_collapses",
"mcp__trust-check__check_token_creator",
"mcp__trust-check__deep_token_safety_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 trust-check. Review it before you use it.
Capability tags behind 5 rules
- mcp__trust-check__check_token_safety untrusted-input
- mcp__trust-check__check_address_safety untrusted-input
- mcp__trust-check__recent_liquidity_collapses untrusted-input
- mcp__trust-check__check_token_creator untrusted-input
- mcp__trust-check__deep_token_safety_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/io.github.gmahar82-stack/trust-check/verify?hash=2111bd9e395420a570696af9a0b9e899770284c78df5e17a85ac7a13a1b547ba" | jq -e '.changed == false'Pinned hash 2111bd9e3954, from Nov 20, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.gmahar82-stack/trust-check/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.gmahar82-stack/trust-check)Source: MCP Registry. Synced Oct 21, 2026, 18:34 UTC.
Trust Check MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Trust Check MCP server safe?
- No scan can promise that. What its definitions show: 5 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 Trust 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 Trust 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 Trust Check MCP server have?
- 5 tools: 5 write. check_token_safety, check_address_safety, recent_liquidity_collapses, check_token_creator and deep_token_safety_report.
Does the Trust Check MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Trust 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 Trust Check 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.