
Publicaml
io.github.publicamlPublished by GitHub account publicamlv0.1.1Updated Oct 24, 2026
AML screening for crypto addresses: risk, sanctions, fund tracing and counterparties.
Overview
Lets an assistant screen crypto addresses for AML risk, sanctions and fund flows across bitcoin, ethereum, bsc and tron via PublicAML.
- What you can do
- Provides three tools backed by the PublicAML intelligence API. screen_address returns risk level and score, sanctions and issuer freezes, the address type (exchange, mixer, gambling, bridge, personal wallet) and where the risk comes from. trace_funds walks funding backwards to find who paid a wallet, or forwards to see where money left; list_counterparties classifies counterparties, answers whether a wallet touched an exchange, mixer or casino, and checks suspect addresses against it. Answers are bounded by time and may be marked PARTIAL.
- When to use it
- Useful when an assistant needs to check a crypto wallet before a transaction, investigate where funds came from or went, or see which venues a wallet has dealt with. It suits compliance-style research and due diligence on addresses in the four supported chains.
- Requirements
- Runs locally as a Node.js process via npx (package @publicaml/mcp-server), typically configured in Claude Desktop, Cursor or Claude Code. Network access to the PublicAML API is required. No account is needed; an optional PUBLICAML_API_KEY raises the rate limit and unlocks outgoing tracing. Optional settings include PUBLICAML_API_BASE, PUBLICAML_TIMEOUT_MS and PUBLICAML_TRACE_CONTINUES.
Installation
In SourceWeft
- Open Publicaml in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
PublicAML MCP server
Blockchain AML screening inside Claude Desktop, Cursor, or any other MCP client. Ask about an address in plain language and the assistant checks it against PublicAML: sanctions, issuer freezes, risk propagated through the transaction graph, who funded the wallet and who it dealt with.
Chains: bitcoin, ethereum, bsc, tron.
Works without an account. An API key only lifts the rate limit and unlocks forward tracing.
Install
Claude Desktop, claude_desktop_config.json:
With an API key:
Cursor uses the same block in .cursor/mcp.json. Claude Code:
Tools
screen_address
Risk level and score, sanctions, Tether/Circle freezes, what the address is (exchange, mixer, gambling, bridge, personal wallet) and where its risk comes from.
chain is optional. Omit it and every chain the address format allows is
screened, each result labelled with its chain: the same 0x… string is a
different wallet on ethereum, bsc and tron, so it is never guessed silently.
trace_funds
direction: "incoming" walks the funding backwards to answer "who paid this
wallet", stopping at labelled entities rather than walking into an exchange's
other customers. direction: "outgoing" follows the largest outgoing flows to
where the money left the chain's anonymous part. Outgoing needs an API key.
The walk is bounded by wall clock, so an incomplete answer is returned rather than a timeout, and the answer says which one it is.
list_counterparties
Three questions, one tool. classify enumerates counterparties and says what
each one is (person, venue, hub, deposit address, contract, mint/burn).
category answers "did this wallet touch any exchange / mixer / casino".
check tests a list of suspect addresses against the wallet.
Reading the answers
sanctioned: trueis a blocking fact on its own, whatever the score says.- The score is a risk reading 0-100, never a share of the funds, and its parts combine by MAX, so the breakdown does not add up to the total.
- An address absent from the data comes back as NOT FOUND. That is unknown, not clean.
- Lists are ranked and capped. A
PARTIALanswer is a floor, not a census. - USD figures cover priced tokens only and can be inflated by low-liquidity tokens. Treat them as an order of magnitude.
This is evidence for a human decision, not the decision itself.
Configuration
One-click desktop install
The same server is also distributed as an MCPB bundle, which Claude Desktop installs with a double click and no JSON editing. Build it with:
The bundle lands in dist/. Version, description, licence and the tool list are
read from package.json and from the server's own tool definitions, so the
bundle cannot drift from the npm release.
Development
MIT licensed. API docs: https://publicaml.org/api
Source: README.md at commit 2f77e9d
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts