The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Traql listing page.
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.
Requires Node.js 18+.
The server speaks MCP over stdio, so you normally point a client at it rather than running it by hand.
Add to claude_desktop_config.json:
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project) using the same
mcpServers block as above.
Add to .vscode/mcp.json:
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.
| Variable | Required | Default | Description |
|---|---|---|---|
TRAQL_API_KEY | recommended | — | API key from the traql dashboard. Sent as X-API-Key. Unlocks itemized signals and higher limits. |
TRAQL_API_URL | no | https://api.traql.io | Base URL of the API. Point it at your own deployment if you self-host traql. |
TRAQL_TIMEOUT_MS | no | 30000 | Per-request timeout in milliseconds. |
check_addressScores a single address.
| Argument | Type | Required | Description |
|---|---|---|---|
chain | ethereum | bsc | tron | ton | bitcoin | yes | Network the address belongs to. |
address | string | yes | Address in the chain's native format. |
screen_transactionScores both sides of a transfer, in one of two modes:
from and to (optionally amount and asset) to
screen a transfer before broadcasting it. Works on every supported chain.tx_hash alone to look up a transaction that is already
on-chain. Supported on Ethereum, BSC, TRON and TON.| Argument | Type | Required | Description |
|---|---|---|---|
chain | chain enum | yes | Network the transaction belongs to. |
from | string | pre-flight | Sender address. |
to | string | pre-flight | Recipient address. |
amount | string | no | Integer amount in the asset's base units (e.g. 1000000 for 1 USDT). |
asset | string | no | Asset or token symbol, e.g. USDT. |
tx_hash | string | by-hash | Hash of a broadcast transaction. Mutually exclusive with from/to. |
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.
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.
MIT