publicaml MCP server
io.github.saloprj/publicamlsaloprjstreamable-httpv0.1.0Scanned
Free crypto AML/KYT screening for BTC/ETH/BSC/TRON — risk score, sanctions, source of funds.
8 tools: 5 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 8
- 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 publicaml MCP server can do
The publicaml MCP server is published by the GitHub account saloprj. It has 8 tools. It can create or change data (5 tools: screen_address, trace_funds, trace_source_of_funds, screen_transaction and 1 more), but cannot delete data. 3 tools only read.
8 tools bring in text other people can write (screen_address, trace_funds, list_counterparties and 5 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 0.1.0.
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.
8 tools
Changes things 5Claude Code: ask
follow_swapFor one transaction that went through a DEX or aggregator, show the net balance change per address and asset and flag who the swap was actually for.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 For one transaction that went through a DEX or aggregator, show the net balance change per address and asset and flag who the swap was actually for. Use it to continue a trace past a swap. EVM chains (ethereum, bsc). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Follow funds through a swap
screen_addressScreen a crypto wallet address for AML/KYT 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 Screen a crypto wallet address for AML/KYT risk. Returns an AML score (0-100), risk_level (LOW/MEDIUM/HIGH/CRITICAL), what the address is (axes: business, legal_status, asset_control, ...), sanctioned exposure, source-of-funds and the incidents (hacks, scams, reports) the address appears in, with its role in each. Chains: bitcoin, ethereum, bsc, tron, solana (on solana the score uses the address's own evidence only). aml_score null means not assessed, never 0 or clean. Anything under community_claims is one victim's unconfirmed report: quote it as a report, never as who the address is. An incident marked 'community report, not confirmed' accuses nobody; 'victim, not accused' is the opposite of an accusation. report_url is the victim-report form: offer it only if the user lost funds. Read-only: it only looks the address up, it never changes anything.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Screen address for AML risk
screen_transactionScreen one transaction by hash: what moved, who took part, a label and AML risk for every participant, and an overall verdict.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 Screen one transaction by hash: what moved, who took part, a label and AML risk for every participant, and an overall verdict. Pass focus_address (e.g. your own deposit address) to get the verdict from that wallet's point of view. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Screen a transaction
trace_fundsFollow the OUTGOING funds from an address across the chain and report where the money ends up (exchanges, mixers, sanctioned wallets) and how many hops away.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 Follow the OUTGOING funds from an address across the chain and report where the money ends up (exchanges, mixers, sanctioned wallets) and how many hops away. Read-only: it only reads on-chain history, it never moves or changes funds.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Trace outgoing funds
trace_source_of_fundsWalk an address's INCOMING funds backwards to answer 'where did this wallet's money come 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 Walk an address's INCOMING funds backwards to answer 'where did this wallet's money come from'. Stops at labelled entities (exchanges, mixers, services) and reports them with hop distance. Answers source-of-funds questions. Read-only: it only reads on-chain history.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Trace where funds came from
Only reads 3Show 3 read-only tools
explain_risk_pathExplain WHERE an address's AML risk comes from: for each risk source (sanctioned entity, hack, mixer, scam, frozen funds) the chain of wallets the money took from that source to th…Reads text others writeNo findings
Why it is in this group
- The name "explain_risk_path" says "explain": 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 Explain WHERE an address's AML risk comes from: for each risk source (sanctioned entity, hack, mixer, scam, frozen funds) the chain of wallets the money took from that source to this address, hop by hop, with the label of each wallet, the amounts and assets on each link, dates and transaction hashes. Use it when the user asks why an address is risky, where its risk or dirty money came from, or through whom the funds arrived. Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: Explain where an address's risk comes from
list_counterpartiesList the counterparties an address has transacted with — optionally filtered by entity category (cex, mixer, gambling, bridge, ...).Reads text others writeNo findings
Why it is in this group
- The name "list_counterparties" says "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 counterparties an address has transacted with — optionally filtered by entity category (cex, mixer, gambling, bridge, ...). Set with_risk=true to attach AML risk per counterparty. Read-only: it only lists existing on-chain counterparties, it never writes anything.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: List counterparties
list_transactionsA wallet's recent transfers, newest first, with direction and counterparty for each, plus what we know about each counterparty.Reads text others writeNo findings
Why it is in this group
- The name "list_transactions" says "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 A wallet's recent transfers, newest first, with direction and counterparty for each, plus what we know about each counterparty. Optionally only transfers with one kind of counterparty (e.g. 'did this wallet deposit to a casino'). Read-only.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- title: List an address's transfers
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 write8
- 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
- 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://mcp.publicaml.org/mcp: tools/list returned 8 tools to an anonymous client, including screen_address (write), trace_funds (write), trace_source_of_funds (write), screen_transaction (write), follow_swap (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 added, 1 changed.+1 added~1 changedView diff
- Added:explain_risk_pathOnly reads
- Changed:screen_addressChanges thingsdescriptioninputSchema
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http publicaml https://mcp.publicaml.org/mcpclaude mcp add --transport http publicaml https://mcp.publicaml.org/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__publicaml__list_counterparties",
"mcp__publicaml__list_transactions",
"mcp__publicaml__explain_risk_path"
],
"ask": [
"mcp__publicaml__screen_address",
"mcp__publicaml__trace_funds",
"mcp__publicaml__trace_source_of_funds",
"mcp__publicaml__screen_transaction",
"mcp__publicaml__follow_swap"
],
"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 publicaml. Review it before you use it.
Capability tags behind 8 rules
- mcp__publicaml__screen_address untrusted-input
- mcp__publicaml__trace_funds untrusted-input
- mcp__publicaml__list_counterparties untrusted-input
- mcp__publicaml__trace_source_of_funds untrusted-input
- mcp__publicaml__screen_transaction untrusted-input
- mcp__publicaml__follow_swap untrusted-input
- mcp__publicaml__list_transactions untrusted-input
- mcp__publicaml__explain_risk_path 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.saloprj/publicaml/verify?hash=7e0f25d76ed8f844b1ad09e3afb8e6e0e6aacfe2cc9cd6546c25b1e0eb02d6ee" | jq -e '.changed == false'Pinned hash 7e0f25d76ed8, from Nov 20, 2026, 11:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.saloprj/publicaml/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.saloprj/publicaml)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:48 UTC.
publicaml MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the publicaml MCP server safe?
- No scan can promise that. What its definitions show: 8 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 publicaml MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the publicaml 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 publicaml MCP server have?
- 8 tools: 5 write, 3 read. screen_address, trace_funds, trace_source_of_funds, screen_transaction, follow_swap, list_counterparties, list_transactions and explain_risk_path.
Does the publicaml MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the publicaml MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the publicaml 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.