CCM
/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

Claude Code Marketplaces

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
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Slot openReach developers building with Claude Code.
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
inference shell
inference shell
create and run specialised agents in minutes
build 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 →
Slot openReach developers building with Claude Code.
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending
CodeRabbitCodeScene MCP Serverbelt - the only tool your agent needsMCP-ready Email Sending

defi-intel

defibabylon/defi-intel
HTTP

Operator-grade DeFi intelligence MCP. - 10 tools vs DefiLlama's basic 4, - adds governance proposals, - RWA attestation scores, - live X/Twitter narrative. - No enterprise subscription - and a one-call operator brief that compiles TVL + yields + stablecoins + governance + market narrative into a single NotebookLM-ready document. Sources: DefiLlama, rwa-attest, gov-scout, Grok x_search. Built for DeFi researchers, protocol contributors, and fund analysts.

DeFi Intelligence MCP

Operator-grade DeFi intelligence for Claude. 11 tools covering live TVL, yield pools, stablecoin flows, governance proposals, RWA attestation scores, X/Twitter market narrative, and a one-call operator brief for NotebookLM.

Listed on Smithery: smithery.ai/servers/defibabylon/defi-intel


Why this exists

DefiLlama's native MCP has 4 basic tools. Nansen and Messari are enterprise-gated. This fills the gap: operator-grade DeFi intelligence accessible to any Claude user, no subscription required for core data.

The get_market_narrative tool adds live X/Twitter sentiment via Grok — the only DeFi MCP that combines on-chain data with real-time social signal.


Tools

ToolDescription
get_top_protocols(limit, chain)Top DeFi protocols by TVL, optional chain filter
get_protocol_tvl(slug)Detailed TVL + change metrics for a specific protocol
get_chain_tvl_ranking(limit)TVL ranking across all blockchain networks
get_top_yield_pools(min_apy, chain, limit)Yield farming pools filtered by APY and chain
get_stablecoin_summary()Market cap and peg status for top 10 stablecoins
get_protocol_fees(slug, days)Fee revenue over N days by protocol
search_protocols(query)Fuzzy search protocols by name, category, or chain
get_rwa_attestation(protocol)RWA-Attest risk scores (8 protocols attested)
get_governance_activity(ecosystem)Active governance proposals by ecosystem
get_market_narrative(topic)Live X/Twitter sentiment on any DeFi topic via Grok
generate_operator_brief(protocols, chains, include_narrative)One-call brief: TVL + yields + stablecoins + governance + narrative + RWA. NotebookLM-ready.

Data sources: DefiLlama, rwa-attest, Grok x_search.


Install via Smithery

npx -y @smithery/cli install defibabylon/defi-intel --client claude

Or add to Claude Desktop claude_desktop_config.json:

{
  "mcpServers": {
    "defi-intel": {
      "type": "http",
      "url": "https://defi-intel.siteflowops.co.za/mcp"
    }
  }
}

Self-host

git clone https://github.com/defibabylon/defi-intel
cd defi-intel
pip install -r requirements.txt
cp .env.example .env        # add XAI_API_KEY for x_search
python3 server.py

Server runs at http://localhost:8086. MCP endpoint: /mcp. Health: /health.

For stdio mode (Smithery local):

python3 server.py --stdio

Environment variables

VariableRequiredDescription
XAI_API_KEYOptionalxAI key for get_market_narrative. Get at console.x.ai
PORTOptionalHTTP port (default: 8086)

Systemd (Linux, persistent)

[Unit]
Description=DeFi Intelligence MCP Server
After=network.target

[Service]
ExecStart=/usr/bin/python3 /path/to/server.py
Restart=always
Environment=XAI_API_KEY=your_key_here

[Install]
WantedBy=multi-user.target

Background

What You Build When the Data Doesn't Exist Yet — the Paragraph article behind this tool.


Related

  • gov-scout — the governance scraper behind get_governance_activity
  • rwa-attest — the attestation scoring engine behind get_rwa_attestation
  • HypeFiltr — weekly market gap intelligence newsletter; this MCP was the first gap actioned
Categories
Documents & KnowledgeSearch & Web CrawlingFinance & CommerceMedia & Entertainment
TransportHTTP
UpdatedMay 25, 2026
View on GitHub
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert
Capacitor - Shared memory for your team’s coding agents.Give your AI the whole web as clean markdowninference shellMake your agent a DeFi expert

Related Documents & Knowledge MCP Servers

View all →
DejaView

dejaview

Store and retrieve facts about entities through a persistent knowledge graph. Maintain long-term context across sessions with natural language querying and timeline tracking. Organize information using structured relationships to build a comprehensive memory system. Get you api key at https://dejaview.io
DejaView

dejaview-bd7a4a52

Store and retrieve facts about entities through a persistent knowledge graph. Maintain long-term context across sessions with natural language querying and timeline tracking. Organize information using structured relationships to build a comprehensive memory system. Get you api key at https://dejaview.io
Extract

dev.averra/extract

URL-to-Markdown API for AI pipelines — clean markdown with metadata and caching.
Kamy

dev.kamy/kamy

Document API for AI-native software: render PDFs, e-sign, PAdES-seal, and verify.
Lattis

dev.lattis/mcp

Search indexed websites, read raw page markdown, and score AI visibility for any site.
ContextLayer

dotnova/context-layer

Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.