CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Hive Aml Screen

srotzin/hive-mcp-aml-screen
HTTPregistry active
Summary

Screens crypto addresses against the OFAC SDN list and applies chain heuristics to generate a 0-100 risk score with severity bands. Exposes three MCP tools: single-address screening at $0.03, bulk screening at $0.025 per address (10 minimum), and a free daily stats endpoint. Pulls fresh OFAC data every 24 hours from treasury.gov, reads live Base mainnet state via RPC to detect mixer contracts, new wallets, high velocity patterns, and Tornado Cash denominations. Returns structured flags with categories like ofac_sdn_match, mixer_contract, and very_new_wallet. Caches results for 24 hours per chain-address pair. Payments settle via x402 in USDC on Base. Purely observational data, never blocks or freezes funds. Reach for this when your agent needs compliant AML signals before executing agent-to-agent transactions.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

hive-mcp-aml-screen

srotzin/hive-mcp-aml-screen MCP server

AML screening broker for the A2A network. Send an address and a chain. Receive a 0–100 observational risk score, an OFAC SDN match flag, and chain-heuristic categories. Cached for 24 hours.

Hive does not block, freeze, or settle. This is observational AML data only. Customer is responsible for compliance decisions.

  • Sources — daily-refreshed OFAC SDN list (treasury.gov), live Base mainnet RPC reads, conservative mixer-contract seed list
  • Scoring — 0–100 with bands (minimal, low, medium, high, critical)
  • Pricing — $0.03 per single address, $0.025 per address for bulk (10-address minimum), settled via x402 in USDC on Base
  • Cache — 24 hours per (chain, address)
  • Mode — inbound only, ENABLE=true by default

The shim is a broker. It returns observational data. It never blocks, freezes, or settles on behalf of a customer, and it never replaces a regulated KYC/AML provider.

Endpoints

MethodPathCostPurpose
POST/v1/aml/screen$0.03Screen one address
POST/v1/aml/bulk$0.025/addr (min 10)Screen many addresses in one call
GET/v1/aml/todayfreeUTC-day counters and OFAC list status
GET/healthfreeLiveness, OFAC list status, pricing
POST/mcp—JSON-RPC 2.0 entry for MCP clients
GET/.well-known/mcp.jsonfreeMCP descriptor
POST/v1/x402/submit—Settle a 402 quote, mint an access token

MCP tools

ToolCostDescription
aml_screen$0.03Single-address screening
aml_bulk_screen$0.025/addrBulk screening, 10-address minimum
aml_todayfreeCounters and OFAC list status

Every response — JSON-RPC and REST alike — carries the disclaimer field:

"disclaimer": "Hive does not block, freeze, or settle. This is observational AML data only. Customer is responsible for compliance decisions."

Quickstart

curl -sX POST https://hive-mcp-aml-screen.onrender.com/v1/aml/screen \
  -H 'content-type: application/json' \
  -d '{"address":"0x8589427373d6d84e98730d7795d8f6f8731fda16","chain":"base"}'

The first call returns a 402 envelope with a quote. Settle on Base in USDC, then resubmit the proof to /v1/x402/submit to mint an access token, and replay the request with X-Hive-Access: <token>.

curl -sX POST https://hive-mcp-aml-screen.onrender.com/v1/x402/submit \
  -H 'content-type: application/json' \
  -d '{"nonce":"...","payer":"0x...","chain":"base","tx_hash":"0x..."}'

Response shape

{
  "ok": true,
  "address": "0x8589427373d6d84e98730d7795d8f6f8731fda16",
  "chain": "base",
  "risk_score": 100,
  "risk_band": "critical",
  "flags": [
    {"category": "ofac_sdn_match", "severity": "critical", "detail": "OFAC SDN list match: program=CYBER2 sdn_uid=12345"},
    {"category": "mixer_contract", "severity": "high", "detail": "address is a known mixer/sanctioned-protocol contract"}
  ],
  "sdn_match": true,
  "sdn_record": {"sdn_uid": "12345", "sdn_name": "TORNADO CASH", "program": "CYBER2"},
  "chain_detail": {"nonce": 0, "is_contract": true, "balance_wei": "0", "head_block": 12345678},
  "sources": {
    "ofac_sdn": {"list_size": 8421, "last_refresh_ms": 1745798400000},
    "heuristics": {"chain": "base", "version": "v1"}
  },
  "cache_hit": false,
  "cache_ttl_seconds": 86400,
  "screened_at": 1745875200000,
  "screening_id": "8a3f...",
  "disclaimer": "Hive does not block, freeze, or settle. This is observational AML data only. Customer is responsible for compliance decisions."
}

Heuristics

For EVM chains the shim performs four real Base RPC reads — getTransactionCount, getCode, getBalance, getBlockNumber — plus a binary search over historical blocks to estimate the wallet's earliest activity. Categories returned in flags:

CategorySeverityTrigger
ofac_sdn_matchcriticalAddress appears in the daily OFAC SDN list
mixer_contracthighAddress is a known mixer/sanctioned-protocol contract
very_new_walletmediumFirst on-chain activity within 24 hours
high_velocitymedium≥ 20 outbound tx per hour over wallet lifetime
mixer_adjacent_balancelowBalance is exactly 0.1 / 1 / 10 / 100 ETH (Tornado pool denominations)
no_outbound_historylowAddress has never sent a transaction on this chain
rpc_unavailablelowRPC read failed; SDN-only signal returned
heuristic_errorlowInternal heuristic error; SDN-only signal returned

Non-EVM chains return the SDN match signal only with a note in chain_detail.

Configuration

EnvDefaultPurpose
PORT3000HTTP port
ENABLEtrueMaster switch. Set false to short-circuit all paid endpoints with 503
WALLET_ADDRESS0x15184bf50b3d3f52b60434f8942b7d52f2eb436ex402 settlement recipient (W1 MONROE)
BASE_RPC_URLhttps://mainnet.base.orgBase mainnet RPC for chain heuristics
OFAC_SDN_URLhttps://www.treasury.gov/ofac/downloads/sdn.csvSource URL for the SDN list
DB_PATH/tmp/aml.dbSQLite database file
MIXER_ADDRESSES(empty)Comma-separated list of extra mixer contract addresses to flag
X402_BYPASS(unset)Set to any value to bypass payment in development

Persistence

SQLite at /tmp/aml.db with WAL journaling.

  • ofac_sdn — (address PK, sdn_uid, sdn_name, program, list_type, inserted_at) — wiped and re-inserted on each refresh
  • ofac_meta — refresh timestamp, count, byte size, last error
  • screenings — every screen call, billed or cached
  • cache — (chain:address) → JSON payload, 24-hour TTL

Operational notes

  • The OFAC list is refreshed at boot and every 24 hours thereafter
  • Cache entries are pruned hourly
  • Body limit is 256 KB on JSON requests
  • Inbound only — the shim never initiates outbound calls beyond the OFAC fetch and Base RPC reads

License

MIT — see LICENSE.

Hive Civilization Directory

Part of the Hive Civilization — agent-native financial infrastructure.

  • Endpoint Directory: https://thehiveryiq.com
  • Live Leaderboard: https://hive-a2amev.onrender.com/leaderboard
  • Revenue Dashboard: https://hivemine-dashboard.onrender.com
  • Other MCP Servers: https://github.com/srotzin?tab=repositories&q=hive-mcp

Brand: #C08D23

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
AI & LLM Tools
Registryactive
TransportHTTP
UpdatedApr 28, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
SkillFM LLM Cost Optimizer

io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Llm Orchestration Agent

io.github.mikerawsonnz/llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Authenticated Llm Agent

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Copilot Memory MCP

labforgedev/copilot-memory-mcp

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
1
Agent Prompt Injection Firewall Mcp

csoai-org/agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Authenticated Multi Llm Agent

io.github.mikerawsonnz/authenticated-multi-llm-agent

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f