Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Blockchain AML for AI agents: risk scoring, sanctions, tx & bridge tracing across 12 chains.
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.
CHAINANALYZER_API_KEY, X402_PRIVATE_KEY, X402_NETWORK, CHAINANALYZER_BASE_URLValues 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": {
"chainanalyzer": {
"command": "npx",
"args": [
"-y",
"chainanalyzer-mcp"
],
"env": {
"CHAINANALYZER_API_KEY": "your-value",
"X402_PRIVATE_KEY": "your-value",
"X402_NETWORK": "your-value",
"CHAINANALYZER_BASE_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add chainanalyzer --env CHAINANALYZER_API_KEY=your-value --env X402_PRIVATE_KEY=your-value --env X402_NETWORK=your-value --env CHAINANALYZER_BASE_URL=your-value -- npx -y chainanalyzer-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"chainanalyzer": {
"command": "npx",
"args": [
"-y",
"chainanalyzer-mcp"
],
"env": {
"CHAINANALYZER_API_KEY": "your-value",
"X402_PRIVATE_KEY": "your-value",
"X402_NETWORK": "your-value",
"CHAINANALYZER_BASE_URL": "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": {
"chainanalyzer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"chainanalyzer-mcp"
],
"env": {
"CHAINANALYZER_API_KEY": "your-value",
"X402_PRIVATE_KEY": "your-value",
"X402_NETWORK": "your-value",
"CHAINANALYZER_BASE_URL": "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.
X402_NETWORK envCHAINANALYZER_BASE_URL 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 6, 2026
The registry name was verified with the GitHub account rascal-3, which owns the repo
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: CHAINANALYZER_API_KEY, X402_PRIVATE_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 (1.7.0) reached the registry 3 days 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, Reelsaw
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 self-hosted Reelsaw: turn long videos into vertical clips, edit, re-render and export them.
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.
MCP Server for ChainAnalyzer — multi-chain blockchain AML risk analysis for AI agents.
Scan any address across 12 chains, all live for self-serve — Bitcoin, Ethereum, Polygon, BNB Smart Chain, Base, Arbitrum, Optimism, Avalanche, Solana, Kaia, TRON, and XRP. 76+ detection rules, ML anomaly scoring, and Neo4j graph analysis.
| Tool | Description | Price |
|---|---|---|
check_address_risk | AML risk score for any blockchain address | $1.00 |
sanctions_check | OFAC / FATF / JFSA sanctions screening | $0.50 |
hack_exposure_lookup | Is this address connected to a known hack (e.g. Binance 2026)? Verdict, hop distance from the attacker, role and lower-bound amounts per incident (EVM, TRON, Solana, Bitcoin) | $0.50 |
freeze_status | Is this address frozen / blacklisted by a stablecoin issuer (USDT, USDC, JPYC ...)? Current state per token with timestamps | $0.10 |
hack_exposure_batch | Known-hack exposure for up to 50 addresses in one call (deposit-list screening) | $5.00 |
trace_transaction | Transaction flow tracing with ML anomaly detection | $3.00 |
detect_coinjoin | CoinJoin / mixing pattern detection (Bitcoin) | $1.00 |
cluster_wallet | Wallet clustering via Neo4j graph analysis | $2.50 |
batch_screening | Batch AML screening (up to 50 addresses) | $5.00 |
bridge_flow_trace | Multi-hop cross-chain forensic trace with Solver detection + same-intent correlation (NEAR Intents / Wormhole / Stargate / Across / Synapse / Hop / deBridge) | $3.00 |
Ready-to-use tools for LangChain, OpenAI Agents SDK, Vercel AI SDK and ElizaOS (pay per call over x402 or with an API key): examples/.
Add to your MCP configuration:
{
"mcpServers": { "chainanalyzer-aml": { "command": "npx", "args": ["-y", "chainanalyzer-mcp"], "env": { "CHAINANALYZER_API_KEY": "tfk_your_api_key" } } } }
git clone https://github.com/rascal-3/chainanalyzer-mcp.git
cd chainanalyzer-mcp npm install npm start
The repo ships an Agent Skill that tells the agent *when* to use these tools, how to pick the chain from the address format, which tool to call first, and how to report results. It works with any agent that reads SKILL.md (Claude Code, Cursor, Codex CLI, Gemini CLI, OpenClaw, ...).
/plugin marketplace add rascal-3/chainanalyzer-mcp
/plugin install chainanalyzer-aml@chainanalyzer
Set CHAINANALYZER_API_KEY in your shell environment (or X402_PRIVATE_KEY for pay-per-request). The plugin's .mcp.json reads it from there.
Copy skills/chainanalyzer-aml/ into your agent's skills directory and configure the MCP server as shown in Quick Start.
Listed in the official MCP Registry as io.github.rascal-3/chainanalyzer-mcp.
Choose one of three modes:
Create a tfk_ API key at chain-analyzer.com → Account → Settings → API Keys. Every plan can issue keys; the Free plan includes 10 scans/month, enough to try sanctions, risk, trace, CoinJoin and cluster before paying. batch_screening needs Starter or above and bridge_flow_trace needs Business or above in API-key mode (x402 mode has no plan gates). Rate limits by plan: Free 10/min, Starter 30/min, Pro 60/min, Business 120/min, Enterprise 300/min.
{
"env": { "CHAINANALYZER_API_KEY": "tfk_your_api_key" } }
No account needed. Pay with USDC on Base or Solana per request.
{
"env": { "X402_PRIVATE_KEY": "your_wallet_private_key", "X402_NETWORK": "base" } }
Requires the x402 npm package: npm install x402
No authentication. Works when the ChainAnalyzer server has X402_ENABLED=false.
{
"env": { "CHAINANALYZER_BASE_URL": "http://localhost:3000" } }
| Variable | Description | Required |
|---|---|---|
CHAINANALYZER_API_KEY | tfk_ API key (any plan, Free included) | One of API key or x402 |
X402_PRIVATE_KEY | Wallet private key for USDC payments | One of API key or x402 |
X402_NETWORK | Payment network: base or solana (default: base) | No |
CHAINANALYZER_BASE_URL | API base URL (default: https://chain-analyzer.com) | No |
Once configured, ask your AI agent:
"Check if this Ethereum address is sanctioned: 0x1234..."
"Analyze the risk score for this Solana wallet: ABC123..."
"Trace the fund flow of this Bitcoin transaction and check for mixing patterns"
"Screen these 20 addresses for AML compliance"
The agent will automatically call the appropriate ChainAnalyzer tools.
All 12 chains are live for self-serve plans.
| Chain | Highlights |
|---|---|
| Bitcoin | OFAC screening, dust attacks, peel chains, CoinJoin detection |
| Ethereum | 18+ detectors, Neo4j graph analysis, sanctions, mixers |
| Polygon / BNB Smart Chain / Base / Arbitrum / Optimism / Avalanche / Kaia | Full EVM AML suite, bridge tracing |
| Solana | Token security (rug pull, honeypot), wallet drainer detection, bridge tracing |
| TRON | USDT flow screening, sanctions (independent scanner) |
| XRP | Exchange / issuer labels, sanctions (independent scanner) |
bridge_flow_trace supports EVM chains, Solana and Kaia. detect_coinjoin is Bitcoin only.
MIT - see LICENSE
Built by refinancier, inc.