Scytheradar Mcp

io.github.onchainvanguardPublished by GitHub account onchainvanguardv0.1.2Updated Nov 3, 2026

Read-only bilingual screening, blacklist, fund tracing, rug-pull forensics. TRON dirty-USDT + EVM.

VerifiedSTDIODesktop only

Overview

Scytheradar's local MCP server; no sign-in required; STDIO.

No AI overview yet: these facts come from the registry entry and the server itself.

Installation

In SourceWeft

  1. Open Scytheradar Mcp in the dashboard and add it to a workspace.
  2. 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

ScytheRadar MCP

On-chain risk intelligence for AI agents — read-only, bilingual (中文/English), and built for the Chinese-speaking agent ecosystem first. Screen wallets, check blacklists, and trace fund flows, with rug-pull forensics no other crypto MCP ships.

Read-only by design. No private keys, no signing, no transaction execution. The worst case is a wrong answer; your funds are never at risk.

Why ScytheRadar (vs the 15+ crypto-AML MCPs)

We win where they don'tThe gap we fill
🀄 Chinese agent ecosystem firstFirst mover for Coze / Dify / Chinese Claude & Cursor users — bilingual tool descriptions and docs. Every competitor is English-only.
🪦 Rug-pull forensics (death files)87+ rug-pull case files with autopsy reports, timelines, and scam-contract code breakdowns — not just a score, a case file.
💧 TRON 脏U (dirty-USDT) focusTether's official freeze list (9,000+ addresses) + OFAC multi-chain sanctions — built for Asia's P2P/OTC "should I accept this USDT" reality.
💰 Cheap, read-only, keyless trial6 free calls/day, no signup; paid plans from a few USDT. Built for retail users and small merchants, not banks.

Tools

ToolWhat it does
screen_addressRisk-screen a wallet address (0-100 score / level / verdict / risk flags)
check_blacklistBlacklist hit check (Tether freezes / OFAC sanctions / phishing)
trace_fundsFund tracing (flow / hops / aggregation / suspected laundering path)

Language

Tool descriptions are bilingual (中文 / English), so Chinese-language agents (Coze, Dify, 文心, Kimi) call the right tool just as reliably as English ones. 工具描述中英双语,中文 agent 同样能精准调用。

Quick start

1. Get an API key

Grab a free key at https://scytheradar.com/b2b. Without a key you get a limited trial (6 calls/day); with a key you unlock full coverage.

2. Claude Desktop

Add to your Claude Desktop MCP config:

json
{  "mcpServers": {    "scytheradar": {      "command": "npx",      "args": ["-y", "scytheradar-mcp"],      "env": {        "SCYTHERADAR_API_KEY": "your-key"      }    }  }}

3. Cursor

Cursor Settings → MCP → Add new MCP server, command npx -y scytheradar-mcp, env SCYTHERADAR_API_KEY.

4. Run locally

bash
export SCYTHERADAR_API_KEY=your-keynpx -y scytheradar-mcp

Environment variables

VariableDescription
SCYTHERADAR_API_KEYAPI key (required for paid endpoints)
SCYTHERADAR_BASEAPI base URL, defaults to https://scytheradar.com

Coverage

  • Chains: BSC / Ethereum / Base / Arbitrum / TRON (blacklist also covers BTC / LTC / ZEC / XMR / Solana)
  • Data: 9,000+ Tether freeze addresses · 495 OFAC sanctions (multi-chain) · phishing database · 87+ rug-pull death files (autopsy + timeline)

Disclaimer

Research use only. Not investment advice.

Source: README.md at commit b958da1

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestNov 3, 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