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
  • 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

Claudinho

arturogarrido/claudinho
STDIOregistry active
Summary

A fan-built MCP server that pipes 2026 World Cup data into Claude with zero setup. Exposes seven tools: get_today, get_live, get_match, get_next_fixture, get_standings, get_market_signal, and get_share_snippet. All 104 fixtures ship bundled, so the schedule works offline. Live scores pull from ESPN's public scoreboard. The market_signal tool surfaces Polymarket implied probabilities when available, purely informational. No API keys, no signup. Reach for this if you want Claude to answer "when does Mexico play next" or "what's the score" without leaving your editor. Also includes a Claude Code statusline hook that shows live scores inline while you code. Works in any MCP client via stdio transport.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
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 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download 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 →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
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 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download 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 →

Claudinho ⚽

CI npm: @claudinho/cli npm: @claudinho/mcp npm downloads cursor.directory smithery badge Glama: A node license: MIT #VibingLaVidaLoca GitHub stars

Live scores for the 2026 men's football tournament — in your terminal, your Claude Code / Cursor CLI statusline, and any MCP client. No API key, no signup; all 104 fixtures ship bundled, so the schedule works offline.

A Claude Code statusline flipping to a live World Cup score — South Korea 2–1 Czechia — while tests run in the terminal

npx @claudinho/cli today      # try it in 10 seconds — no install, no key
npx @claudinho/cli live       # what's on right now (during match windows)

⭐ Like it? Star the repo — a fan project's only scoreboard is its stars. (claudinho star shows you how anytime.)

While matches are live, your Claude Code or Cursor CLI statusline reads:

⚽ 🇳🇴 1–1 🇫🇷 87' · 🇸🇳 1–2 🇮🇶 86'

And claudinho share prints a card made for the group chat:

Group A · standings

1. 🇲🇽 MEX  9 pts · 3-0-0 · +6
2. 🇿🇦 RSA  4 pts · 1-1-1 · -1
3. 🇰🇷 KOR  3 pts · 1-0-2 · -1
4. 🇨🇿 CZE  1 pts · 0-1-2 · -4

Live data: ESPN
#VibingLaVidaLoca · Independent fan project · not affiliated with FIFA or Anthropic.
Try it: npx @claudinho/cli table A

⚠️ Not affiliated with, endorsed by, or connected to FIFA or Anthropic. Claudinho is an independent, open-source fan project. It displays factual match data (scores, fixtures, standings) and uses emoji flags only — no logos, emblems, kits, broadcast footage, or player likenesses.

Install

Just the CLI

npm i -g @claudinho/cli
claudinho today
claudinho next MEX --tz America/Mexico_City --lang es

Cursor CLI — statusline + MCP

One command wires the live-score statusline and prints the MCP config to paste:

npm i -g @claudinho/cli
claudinho init cursor          # statusline → ~/.cursor/cli-config.json (+ the MCP paste)

A live World Cup score in a Cursor CLI statusline — Uzbekistan 0–1 Colombia, 42' — with a model and context line below it

Restart your agent session to see it. Prefer to paste it yourself? claudinho init cursor --print emits the snippets, or copy them straight from here:

Statusline — ~/.cursor/cli-config.json:

{
  "statusLine": {
    "type": "command",
    "command": "claudinho prompt",
    "padding": 0,
    "updateIntervalMs": 1000,
    "timeoutMs": 1500
  }
}

MCP tools — ~/.cursor/mcp.json (global) or a project .cursor/mcp.json:

{ "mcpServers": { "claudinho": { "command": "npx", "args": ["-y", "@claudinho/mcp"] } } }

Optional env — a model + context line below the score, or scope to your team:

export CLAUDINHO_CURSOR_META=auto   # model + context % line under the score (recommended)
export CLAUDINHO_TEAM=MEX           # show only your team's match
export CLAUDINHO_FLAGS=off          # 3-letter codes instead of flag emoji (already automatic in Warp)
export CLAUDINHO_DEBUG=1            # print data-provider failure diagnostics to stderr

Note: Cursor's beforeSubmitPrompt hook doesn't yet reliably inject context into the model, so the score-aware hook stays Claude Code-only for now — the statusline and MCP server work great in Cursor.

Claude Code — statusline, score-aware hook, MCP

npm i -g @claudinho/cli
claudinho init claude          # statusline + live-score hook, then the MCP one-liner

init claude backs up ~/.claude/settings.json first and is idempotent. Prefer the pieces à la carte? Run init-statusline, init-hook, and:

claude mcp add claudinho -- npx -y @claudinho/mcp

Restart Claude Code to activate.

Monorepo / local dev? The init cursor / init claude aliases wire the global claudinho. To point a statusline or hook at a local build, use the granular commands with --command, e.g. claudinho init-cursor-statusline --command "node ./packages/cli/dist/index.js prompt" (and init-statusline / init-hook for Claude Code).

Other MCP clients — Codex, Claude Desktop, Windsurf, Zed, VS Code

codex mcp add claudinho -- npx -y @claudinho/mcp    # Codex CLI

Everything else takes the standard stdio config:

{ "mcpServers": { "claudinho": { "command": "npx", "args": ["-y", "@claudinho/mcp"] } } }

Then just ask, mid-task — the agent calls the MCP server and answers with the score:

An AI coding agent asked 'did Germany get through?' mid-task — it calls the Claudinho MCP server and answers with the result: Germany 1(3)–1(4) Paraguay, FT (Paraguay won on penalties)

Surfaces

  • CLI — today, live, next MEX, table, match <id>, bracket, markets, share, team (name → code, e.g. team "DR Congo") (plus vibe 😎 and star ⭐). --json on everything; TZ-aware via --tz.
  • Live statusline — Claude Code & Cursor CLI — every live score inline; reads a local micro-cache, never blocks on the network. One command per agent: claudinho init claude / claudinho init cursor (also tmux & Starship via claudinho prompt).
  • Score-aware hook (Claude Code) — a UserPromptSubmit hook that drops the live score into the model's context during matches; zero tokens off-match. (Cursor parity pending — its hook can't reliably inject context yet.)
  • MCP server — 9 read-only tools (get_today, get_live, get_match, get_next_fixture, get_standings, get_bracket, get_market_signal, get_share_snippet, get_team) plus my_team / tournament_today prompts.
  • Prediction-market signals — a read-only "who's favored" line (market-implied percentages, Source: Polymarket), shown only when a reliable market exists. Informational only — not betting advice. Opt out: --no-markets / CLAUDINHO_MARKETS=off.
  • Shareable cards — claudinho share next MEX --copy puts a plain-text match card on your clipboard; claudinho share table A does the same for a group's live standings; claudinho share bracket for the knockout tree.

Speaks en / es / pt / fr, with optional localized commentary flair (¡GOOOOL!) — dial it down with --flavor subtle|off.

Planned (not shipped yet): a desktop notifier and an AI pundit with a public accuracy scorecard.

FAQ

Do I need an API key or account? No. Nothing to sign up for; npx and done.

Does it work offline? The bundled data does — the full schedule, group fixtures, and the knockout bracket structure (all 104 fixtures ship bundled, no key). Anything live hits the network: scores, group standings, and a team's resolved knockout opponent (next once the draw fills in).

Where does the data come from? Live scores from ESPN's public scoreboard (attributed in output as Live data: ESPN); market signals from Polymarket public data. Rate limits respected.

Is the market line betting advice? No. It's read-only, informational-only market data with attribution — no trading, no links — and it never appears on the statusline or hook.

Why no crests, kits, or player photos? Legal-clean by design: facts and emoji flags only.

Flags show as boxed letters (CH, BA)? Some terminals — notably Warp — don't compose the regional-indicator pairs into flag glyphs, so 🇨🇭 renders as a boxed CH. claudinho auto-detects Warp and drops the flags: 3-letter codes on the statusline (MEX 1–0 RSA 67') and plain team names in the hook, today / live / table, and next. Force it anywhere with CLAUDINHO_FLAGS=off, or keep flags with CLAUDINHO_FLAGS=on.

Windows? Works, but flag emoji rendering varies by terminal — best on macOS/Linux. See the flags note above; CLAUDINHO_FLAGS=off gives clean codes on any terminal that can't render them.

Why star?

Claudinho is a solo, $0, organic fan project — a GitHub star is the only signal that it's worth maintaining, and the nudge to keep shipping through the final. A star also:

  • surfaces it for other devs hunting live scores during the tournament,
  • puts new releases in your feed — a desktop notifier, an AI pundit, and other tournaments are on the roadmap,
  • takes one click → ⭐ star Claudinho.

New here? CONTRIBUTING.md has the layout, the dev loop, and good first issues.

Privacy Policy

Claudinho collects no personal data — no accounts, no telemetry, no analytics, no tracking. There is no Claudinho server. To show live results it makes read-only requests to public sports-data services (ESPN for scores/standings; Polymarket for informational-only market signals) with no account or personal data attached, and keeps a small cache in your local cache directory (~/.cache/claudinho). Full details: PRIVACY.md.

License

MIT © 2026 Arturo Garrido. All three packages publish with npm provenance via OIDC trusted publishing.


Built while watching the games. #VibingLaVidaLoca ⚽

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
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 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download 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 →

Configuration

CLAUDINHO_LANG

UI language: en, es, pt, or fr (optional; default en)

CLAUDINHO_TZ

IANA timezone for kickoff times, e.g. America/Mexico_City (optional; default system)

CLAUDINHO_FLAVOR

Commentary flair: off, subtle, or full (optional; default full)

CLAUDINHO_MARKETS

Set to 'off' to hide read-only prediction-market signals (optional; informational only)

Categories
AI & LLM Tools
Registryactive
Package@claudinho/mcp
TransportSTDIO
UpdatedJun 10, 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