
traql
io.traqlPublished by traql.iov0.1.2Updated Oct 24, 2026
AML risk scoring for crypto addresses and transactions on Ethereum, BSC, TRON, TON, Bitcoin
Overview
Scores crypto addresses and transactions for AML risk, returning a 0–100 score, band, flags and signals to an AI assistant.
- What you can do
- Check a single address on Ethereum, BSC, TRON, TON or Bitcoin and get a 0–100 risk score, band and flags
- Screen a transfer before broadcasting it by passing sender, recipient, optional amount and asset
- Look up an already on-chain transaction by hash on Ethereum, BSC, TRON or TON
- Read itemized signals with source, entity, severity and confidence, plus a computed timestamp
- Receive both human-readable text and structured content for each result
- When to use it
- Useful when an assistant helps with crypto payments, treasury or compliance triage and needs a quick risk read on a counterparty address or a transfer before it is sent. Also handy for reviewing an existing transaction hash against sanctions, mixer and scam data.
- Requirements
- Runs locally over stdio via npx, requiring Node.js 18 or later. An API key from the traql dashboard is recommended, set as TRAQL_API_KEY and sent as the X-API-Key header. Optional TRAQL_API_URL for self-hosting and TRAQL_TIMEOUT_MS for request timeouts. Network access to the hosted API is needed.
Installation
In SourceWeft
- Open traql 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
traql MCP server
[npm] [CI] [License: MIT] [Glama] [M8ven Live Monitored] [mcprush]
AML and compliance risk scoring for crypto addresses and transactions, exposed to AI agents over the Model Context Protocol.
Ask your agent "is it safe to send to this address?" and it gets back a 0–100 risk score, a band, the risk categories behind it, and — with an API key — every individual signal with its source and confidence.
Backed by traql: OFAC SDN, UK OFSI, EU and UN sanctions lists, Tether/Circle freeze events, curated hack and mixer attributions, and counterparty exposure analysis across Ethereum, BSC, TRON, TON and Bitcoin.
Quick start
Requires Node.js 18+.
The server speaks MCP over stdio, so you normally point a client at it rather than running it by hand.
Claude Code
Claude Desktop
Add to claude_desktop_config.json:
Cursor
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project) using the same
mcpServers block as above.
VS Code
Add to .vscode/mcp.json:
Getting an API key
Sign up at app.traql.io, confirm your email — free checks are included — and issue a key under API keys. The secret is shown once; it can be rotated or revoked at any time.
Without a key the server still runs, on the keyless tier: the hosted API serves 3 free checks per IP per day so you can try it immediately, then asks for per-call payment over x402. Keyless responses are also coarser — a single reason phrase instead of itemized signals — and rate limits are tighter. For anything beyond a first look, set a key.
Configuration
Tools
check_address
Scores a single address.
screen_transaction
Scores both sides of a transfer, in one of two modes:
- Pre-flight — pass
fromandto(optionallyamountandasset) to screen a transfer before broadcasting it. Works on every supported chain. - By hash — pass
tx_hashalone to look up a transaction that is already on-chain. Supported on Ethereum, BSC, TRON and TON.
Response
Both tools return human-readable text plus structuredContent:
Score bands: clean 0–9, low 10–39, elevated 40–69, high 70–89,
critical 90–100.
partial: true means an upstream data source was degraded while computing the
result — read the score as a lower bound, not a final verdict.
Each successful call consumes one check from the configured account. Malformed input is rejected locally where possible, so it costs nothing.
Development
Notes
Scores are advisory signals for triage and automation. They are not a legal determination of wrongdoing, and they do not by themselves discharge any regulatory obligation.
Links
- traql.io — product
- API documentation
- Dashboard
License
MIT
Source: README.md at commit 3f705bd
Tools
0Version history
1- v0.1.2LatestSep 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