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 Address Screen

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

Connects Claude to Hive's on-chain address risk screening via GoPlus Security's 17-vector analysis. Two tools: address_screen returns full attestation receipts with Ed25519 signatures and patent-backed C18 warranties, while address_screen_clear_only gives you a simple pass/fail boolean. Default chain is Base (8453, USDC rail). Each screen checks cybercrime flags, money laundering signals, phishing history, sanctioned addresses, and 13 other vectors. Reach for this when your agent needs to vet a wallet before executing a transfer or approval. The backend is live at hivemorph.onrender.com, not mocked. Every response includes a cryptographically signed receipt you can verify or store for compliance audit trails.

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-address-screen

Pre-settlement on-chain risk screen for autonomous agents.

17-vector GoPlus address-risk rail. Every response includes an Ed25519-signed C18 attestation receipt from the Hive backend. Real rail on Base (USDC chain ID 8453) — no mocks.

MCP 2024-11-05 Base 8453 GoPlus 17-vector Ed25519 C18 receipt MIT

MCP Tools

ToolInputOutput
address_screenaddress (string, required), chain_id (integer, default 8453)Full backend response: screen_id, address, chain_id, decision (CLEAR|FLAG), flags_hit[], malicious_contracts_created, raw GoPlus data, Ed25519-signed receipt (C18), _meta
address_screen_clear_onlyaddress (string, required), chain_id (integer, default 8453)is_clear (boolean), flags_hit[], decision, screen_id, address, chain_id

Both tools call the same live backend. address_screen_clear_only is a lightweight convenience wrapper that strips the full receipt when you only need a pass/fail signal.


Endpoints

MethodPathDescription
POST/mcpJSON-RPC 2.0 MCP endpoint
GET/healthService health check
GET/.well-known/mcp.jsonMCP discovery manifest
GET/.well-known/agent.jsonA2A agent card
GET/seo.jsonSEO metadata

Backend

FieldValue
EndpointPOST https://hivemorph.onrender.com/v1/attest/address/screen
Body{"address":"<0x...>","chain_id":8453}
ProviderGoPlus Security (17-vector address risk)
ReceiptEd25519-signed (C18 attestation warranty)
Chain (default)Base — chain ID 8453

Example request

curl -X POST https://hivemorph.onrender.com/v1/attest/address/screen \
  -H "Content-Type: application/json" \
  -d '{"address":"0x15184Bf50B3d3F52b60434f8942b7D52F2eB436E","chain_id":8453}'

Example response (CLEAR)

{
  "screen_id": "addrca8431d8-...",
  "address": "0x15184bf50b3d3f52b60434f8942b7d52f2eb436e",
  "chain_id": 8453,
  "decision": "CLEAR",
  "flags_hit": [],
  "malicious_contracts_created": 0,
  "raw": { "cybercrime": "0", "money_laundering": "0", ... },
  "receipt": {
    "kind": "address_risk_screen_receipt",
    "decision": "CLEAR",
    "signing": { "algorithm": "EdDSA", "curve": "Ed25519", ... }
  },
  "_meta": { "patent": "USPTO 64/055,601", "claim": "C23" }
}

Connect

Claude / Cursor / any MCP-compatible host

Add to your MCP config:

{
  "mcpServers": {
    "hive-address-screen": {
      "url": "https://hive-mcp-address-screen.onrender.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Run locally

git clone https://github.com/srotzin/hive-mcp-address-screen.git
cd hive-mcp-address-screen
npm install
node server.js
# Server on :3000

Environment variables

VariableDefaultDescription
PORT3000HTTP listen port
HIVE_BASEhttps://hivemorph.onrender.comHive backend base URL

Protocol

  • Transport: Streamable-HTTP
  • Protocol version: MCP 2024-11-05
  • Message format: JSON-RPC 2.0
  • Methods supported: initialize, tools/list, tools/call, ping

GoPlus Risk Vectors (17)

cybercrime · money_laundering · gas_abuse · financial_crime · darkweb_transactions · reinit · phishing_activities · contract_address · fake_kyc · blacklist_doubt · fake_standard_interface · stealing_attack · blackmail_activities · sanctioned · malicious_mining_activities · mixer · fake_token · honeypot_related_address

A CLEAR decision means all 17 vectors returned "0" and malicious_contracts_created is 0.


License

MIT — see LICENSE.

Patent claim: C23 (USPTO 64/055,601)

Inventor: Stephen A. Rotzin · thehiveryiq.com · steve@thehiveryiq.com

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
UpdatedMay 4, 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