Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
AML risk scoring for crypto addresses and transactions on Ethereum, BSC, TRON, TON, Bitcoin
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
TRAQL_API_KEY, TRAQL_API_URL, TRAQL_TIMEOUT_MSValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"traql": {
"command": "npx",
"args": [
"-y",
"@traql/mcp"
],
"env": {
"TRAQL_API_KEY": "your-value",
"TRAQL_API_URL": "your-value",
"TRAQL_TIMEOUT_MS": "your-value"
}
}
}
}Run this in your terminal
claude mcp add traql --env TRAQL_API_KEY=your-value --env TRAQL_API_URL=your-value --env TRAQL_TIMEOUT_MS=your-value -- npx -y @traql/mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"traql": {
"command": "npx",
"args": [
"-y",
"@traql/mcp"
],
"env": {
"TRAQL_API_KEY": "your-value",
"TRAQL_API_URL": "your-value",
"TRAQL_TIMEOUT_MS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"traql": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@traql/mcp"
],
"env": {
"TRAQL_API_KEY": "your-value",
"TRAQL_API_URL": "your-value",
"TRAQL_TIMEOUT_MS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
TRAQL_API_URL envTRAQL_TIMEOUT_MS envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain traql.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: TRAQL_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.2) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, EmbeddedCI BenchPod
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
ethereum address 0x8589427373d6d84e98730d7795d8f6f8731fda16
RISK 100/100 — CRITICAL Flags: sanctions, mixer, scam
Signals (21): +80 [sanctions/eth_labels] direct.sanctions — sanctions label "Tornado.Cash: Donate" [entity Tornado.Cash: Donate, confidence 0.80] +68 [mixer/eth_labels] direct.mixer — mixer label "Tornado.Cash: Donate" [entity Tornado.Cash: Donate, confidence 0.80] +10 [mixer] behavior.mixer_contact — direct contact with mixer 0xdd4c48c0b24039969fc16d1cdf626eab821d3384 +9 [sanctions/ofac_sdn] indirect.sanctions — sent to Semenov Roman (sanctions, 18% of USDC volume) [entity Semenov Roman, confidence 1.00] ... and 17 more
Computed at 2026-08-23T11:42:49Z.
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+.
npx -y @traql/mcp
The server speaks MCP over stdio, so you normally point a client at it rather than running it by hand.
claude mcp add traql --env TRAQL_API_KEY=your_key -- npx -y @traql/mcp
Add to claude_desktop_config.json:
{
"mcpServers": { "traql": { "command": "npx", "args": ["-y", "@traql/mcp"], "env": { "TRAQL_API_KEY": "your_key" } } } }
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project) using the same mcpServers block as above.
Add to .vscode/mcp.json:
{
"servers": { "traql": { "type": "stdio", "command": "npx", "args": ["-y", "@traql/mcp"], "env": { "TRAQL_API_KEY": "your_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.
| 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:
{
"subject": { "type": "address", "chain": "ethereum", "address": "0x…" }, "result": { "score": 100, "band": "critical", "flags": ["sanctions", "mixer", "scam"], "partial": false, "computed_at": "2026-08-23T11:42:49Z", "reasons": [ { "code": "direct.sanctions", "message": "sanctions label \"Tornado.Cash: Donate\" from eth_labels (severity 100 × confidence 0.80 = 80.0)", "contribution": 80, "category": "sanctions", "source": "eth_labels", "entity": "Tornado.Cash: Donate", "severity": 100, "confidence": 0.8, "eff": 80.0 } ] } }
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.
npm install
npm run build npm test
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