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
shawn5cents avatar

Agentskin

shawn5cents/agentskin
authSTDIOregistry active
Summary

This is a local proxy layer that sits between Claude and any HTTP endpoint you're hitting. It exposes two tools: fetch_optimized_data pulls from APIs or web URLs and strips out verbose keys you don't need, returning compact Markdown instead of bloated JSON, and skin_reasoning compresses natural language by removing filler words. You pass in the URL plus optional signals (keys to keep) and aliases (renames for consistency). The repo claims 70% token reduction on typical API responses. It includes SSRF protection, rate limiting, and blocks cloud metadata endpoints. Reach for this when you're burning tokens on repetitive API calls with huge payloads where you only need a handful of fields, or when chaining multiple web requests in a reasoning loop.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
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 →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
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 →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
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 →
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 →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
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 →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
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 →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
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 →
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 →

AgentSkin Suite

npm version License: MIT

The complete token optimization stack for AI coding agents. Three complementary tools that eliminate the "Token Tax" across the full agent cycle — API responses, CLI output, and agent replies.

The Suite

ComponentWhat It DoesSavingsCreator
AgentSkin SSSSemantic JSON pruning via MCP60–88% on rich APIsShawn Nichols Sr.
Tokenjuice CLIRule-driven terminal output compactionUp to 99.97% on large outputsVincent Koc (MIT)
CavemanOutput compression via prompt engineering65% output reductionJulius Brussee

Quick Start

# 1. AgentSkin MCP server
npx -y agentskin@latest

# 2. Bash hook (transparent CLI optimization)
source .agents/hooks/bash-optimizer.sh

# 3. Caveman — already active via AGENTS.md

By the Numbers

MetricValue
GitHub API savings88.3% (1,544 → 180 tokens)
ls -laR directory listing99.97% (3.19M → 897 chars)
Caveman output compression65% average
Caveman memory compression46% smaller
MCP tools7 across unified server
Combined test suite4,695 tests, 274 files — 100% passing
Pipeline throughput3,030 fixtures/sec (0.33ms avg)
Net session savings17.1% (zero overhead via bash hook)

Tools

AgentSkin Suite MCP (7 tools, unified)

fetch_optimized_data · skin_reasoning · classify_url · strip_ansi · reduce · estimate_tokens · apply_json_semantic

Caveman Skills (6 skills)

caveman · caveman-commit · caveman-review · caveman-stats · caveman-compress · cavecrew

Documentation

DocDescription
OVERVIEW.mdProject overview and quick start
ARCHITECTURE.mdTechnical architecture and data flow
STATUS.mdPhase completion and test coverage
BENCHMARK.mdLive API compression benchmarks
USAGE.mdFull usage guide — hook, caveman, MCP
THREE-LAYER-RULES.mdRule config override semantics
AUTHORS.mdCredits and component details

Security

  • SSRF Protection: Blocks private IPv4/IPv6 ranges and cloud metadata services
  • Rate Limiting: 60 req/min sliding window
  • Input Validation: Zod schemas for all tool inputs
  • Processing Timeout: 30-second limit

Credits

CreatorContribution
Shawn Nichols Sr. (Nichols Transco LLC)AgentSkin SSS protocol, MCP server, Suite integration
Vincent KocTokenjuice — MIT License
Julius BrusseeCaveman — github.com/JuliusBrussee/caveman

Website

agentskin.dev — Protocol specification, examples, FAQ, and whitepaper.


© 2026 Nichols Transco LLC.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
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 →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
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 →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
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 →
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 →

Configuration

BRAVE_SEARCH_API_KEYsecret

Brave Search API Key

SERPER_API_KEYsecret

Serper.dev Search API Key

TAVILY_API_KEYsecret

Tavily Search API Key

APILAYER_KEYsecret

MediaStack API Key

Categories
Data & Analytics
Registryactive
Packageagentskin
TransportSTDIO
AuthRequired
UpdatedMar 13, 2026
View on GitHub

Related Data & Analytics MCP Servers

View all →
shibui avatar
Shibui Finance

shibui/finance

## Server Description Screen 9,900+ US equities across 64 years of daily prices, quarterly financials, and 56 technical indicators. Describe what you're looking for in plain English and Shibui translates it into SQL against a 31M-row database. Combine multi-year margin consistency, revenue growth trends, RSI and MACD signals, balance sheet strength, valuation ratios, and earnings surprises in a single query. Examples: - "Find companies under $5B market cap where operating margins stayed above 15% every year since 2019 with revenue growth in at least 4 of those years" - "Which stocks just crossed below their 200-day SMA with RSI under 30 but had positive free cash flow last quarter?" - "Compare NVDA vs AMD on revenue growth, gross margins, and EV/EBITDA over the last 3 years" ### Coverage - **Symbols:** 9,900+ (NYSE + NASDAQ) - common stocks, ETFs, ADRs, REITs - **Prices:** ~31M daily OHLCV records since 1962 - **Financials:** Quarterly and annual income statements, balance sheets, cash flow (1990-present) - **Valuation:** Daily P/E, P/B, market cap, enterprise value, EV/EBITDA, FCF yield (1993-present) - **Technical indicators:** 56 pre-calculated (RSI, MACD, Bollinger Bands, SMA, EMA, ADX, candlestick patterns, and more) - **Earnings:** Quarterly EPS actuals, estimates, and surprise percentages - **Analyst estimates:** Target prices, buy/hold/sell ratings - **Ownership:** Institutional holdings, short interest ### Access Free. No API key. Remote MCP server at `https://mcp.shibui.finance/mcp`. Connect in under 2 minutes.
shibui avatar
Shibui Finance

shibui/finance-2c912dc8

## Server Description Screen 9,900+ US equities across 64 years of daily prices, quarterly financials, and 56 technical indicators. Describe what you're looking for in plain English and Shibui translates it into SQL against a 31M-row database. Combine multi-year margin consistency, revenue growth trends, RSI and MACD signals, balance sheet strength, valuation ratios, and earnings surprises in a single query. Examples: - "Find companies under $5B market cap where operating margins stayed above 15% every year since 2019 with revenue growth in at least 4 of those years" - "Which stocks just crossed below their 200-day SMA with RSI under 30 but had positive free cash flow last quarter?" - "Compare NVDA vs AMD on revenue growth, gross margins, and EV/EBITDA over the last 3 years" ### Coverage - **Symbols:** 9,900+ (NYSE + NASDAQ) - common stocks, ETFs, ADRs, REITs - **Prices:** ~31M daily OHLCV records since 1962 - **Financials:** Quarterly and annual income statements, balance sheets, cash flow (1990-present) - **Valuation:** Daily P/E, P/B, market cap, enterprise value, EV/EBITDA, FCF yield (1993-present) - **Technical indicators:** 56 pre-calculated (RSI, MACD, Bollinger Bands, SMA, EMA, ADX, candlestick patterns, and more) - **Earnings:** Quarterly EPS actuals, estimates, and surprise percentages - **Analyst estimates:** Target prices, buy/hold/sell ratings - **Ownership:** Institutional holdings, short interest ### Access Free. No API key. Remote MCP server at `https://mcp.shibui.finance/mcp`. Connect in under 2 minutes.
shin1219-eng avatar
Browser Proof

shin1219-eng/browser-proof

Evidence-backed web verification for agents with deterministic JSON, text evidence, and screenshots.
sidneybissoli avatar
Senado Br Mcp

sidneybissoli/senado-br-mcp

MCP Server for Brazilian Federal Senate open data (legislators, bills, votes)
sincetomorrow avatar
cultural-intelligence

sincetomorrow/cultural-intelligence

The cultural GPS for AI commerce. 504,472 aesthetic worlds mapped across 193 dimensions — from dark academia to k-beauty to quiet luxury. 3,154 autonomous agents update intelligence every 48 hours. 9 tools: product recommendations with affiliate links, brand cultural position, trend intelligence, commerce gap predictions, world comparisons, and live cultural signals. Free. Open source. MIT licensed. 14 AI companies already consume our data at 33,000+ requests/hour. Open Source Commerce For All.
siriuslattice avatar
Evmcp

siriuslattice/evmcp

Multi-chain EVM blockchain data with companion smart contracts