Everything Ai Coding
by
Curated catalog of AI coding resources—including MCP servers, reusable skills, rule sets, and prompt templates—plus a CLI tool for one‑command search, browse, and installation directly from AI agents.
Everything Ai Coding Overview
What is Everything Ai Coding about?
A continuously updated knowledge base that aggregates, deduplicates, scores, and publishes over 4,000 AI‑coding resources from 9+ upstream sources. Each entry is enriched with quality signals (coding relevance, content quality, source trust, community popularity) so developers can evaluate before installing.
How to use Everything Ai Coding?
- Install the CLI – run the platform‑specific installer (macOS/Linux
curl ... | bash, Windows PowerShellirm ... | iex). The script auto‑detects the host platform (Claude Code, Costrict, Opencode, VSCode Costrict) or you can specify--platform <name>. - Search – e.g.
/everything-ai-coding-search typescript(Costrict/Opencode/VSCode) or/everything-ai-coding:search typescript(Claude Code). Addtype:mcp|skill|rule|promptto filter. - Browse –
/everything-ai-coding-browse [category]. - Recommend –
/everything-ai-coding-recommendto get suggestions based on the current project stack. - Install / Uninstall / Update – use
/everything-ai-coding-install <id>,/everything-ai-coding-uninstall <id>,/everything-ai-coding-update. - Verify – run a search command; a markdown table of matching resources confirms successful installation.
Key Features
- Unified catalog of MCP servers, skills, rules, and prompts (1627 servers, 1645 skills, 236 rules, 532 prompts).
- Quality scoring (0–100) combining relevance, documentation, source trust, and community signals.
- Weekly sync pipeline that pulls from upstream repos, deduplicates, enriches, and republishes.
- Interactive web UI hosted at https://zgsm-ai.github.io/everything-ai-coding/ for visual browsing.
- One‑command installers for macOS, Linux, and Windows; supports four AI‑coding platforms.
- Search index served as a lightweight JSON file for fast agent queries.
- Extensible – contributors can add resources by PRing to
catalog/following the provided schema.
Use Cases
- AI agent developers need a reliable source of MCP servers and skills to extend their assistants.
- DevOps teams can quickly install security or performance rule sets across repositories.
- Prompt engineers browse ready‑made prompt templates for common coding tasks (e.g., unit‑test generation, SQL query generation).
- Continuous integration pipelines fetch the latest server or skill definitions via the CLI for automated setup.
- Researchers analyze the aggregated quality scores to study trends in AI‑assisted development tools.
FAQ
Q: Do I need to clone the repository to use the catalog? A: No. The installer fetches only the necessary files; the full catalog is also available as JSON via the web API.
Q: Can I add my own custom MCP server or skill?
A: Yes. Submit a pull request to the appropriate catalog/ subdirectory following catalog/schema.json.
Q: Which platforms are supported? A: Claude Code, Costrict CLI, Opencode, and VSCode Costrict (Roo Code). The CLI adapts its command syntax per platform.
Q: How often is the catalog refreshed? A: Weekly via GitHub Actions that run the sync‑merge‑evaluate‑publish pipeline.
Q: Is there a license concern for third‑party resources? A: The catalog only indexes public resources; each entry retains its original license. Review the upstream repository before using.
Everything Ai Coding's README
Why Everything AI Coding?
AI coding agents are improving fast, but the ecosystem around them is still fragmented. Finding a reliable MCP server, reusable skill, practical rule set, or prompt collection usually means searching across multiple repositories and formats.
Everything AI Coding is a curated knowledge base that continuously collects, deduplicates, enriches, and scores resources from 9+ upstream sources. Every entry includes quality signals — source trust, coding relevance, content quality, freshness, and community popularity — so you can evaluate before you install. Browse right here on GitHub, explore interactively with the web catalog, or search and install with one command using the Coding Hub tool.
📚 Knowledge Base
🔌 MCP Servers — 1627 entries
Model Context Protocol servers that connect AI agents to external tools, databases, and services.
| Name | ⭐ Stars | Score | Description |
|---|---|---|---|
| server-filesystem | 83.6k | 93 | Official reference — local filesystem access |
| playwright-mcp | 30.5k | 82 | Browser automation and testing by Microsoft |
| github-mcp-server | 28.7k | 88 | Deep GitHub API integration for workflows |
| pydantic-ai/mcp-run-python | 16.3k | 97 | Run Python in a secure sandbox |
| FastAPI-MCP | 11.7k | 82 | Expose FastAPI endpoints as MCP tools |
Browse all MCP servers → · Browse interactively →
🎯 Skills — 1645 entries
Reusable agent capabilities and workflows for AI coding assistants.
| Name | Source | Score | Description |
|---|---|---|---|
| claude-api | Anthropic Official | 96 | Build and debug Claude API / Anthropic SDK apps |
| mcp-builder | Anthropic Official | 96 | Guide for creating high-quality MCP servers |
| webapp-testing | Anthropic Official | 96 | Test local web apps with Playwright |
| acceptance-orchestrator | Antigravity Skills | 92 | End-to-end from requirements to deploy verification |
| agentic-actions-auditor | Antigravity Skills | 92 | Audit GitHub Actions for AI agent security |
Browse all skills → · Browse interactively →
📋 Rules — 236 entries
Coding conventions and AI behavior guidelines for consistent development.
| Name | Source | Score | Category |
|---|---|---|---|
| Security Audit Rules | Curated | 94 | security |
| Flutter & Dart Rules | CursorRules | 90 | mobile |
| Supabase Rules | CursorRules | 90 | database |
| Disaster Recovery Plan | Rules 2.1 | 88 | tooling |
| Performance Monitoring System | Rules 2.1 | 88 | devops |
Browse all rules → · Browse interactively →
💡 Prompts — 532 entries
Developer-focused prompt templates for common coding tasks.
| Name | Source | Score | Category |
|---|---|---|---|
| Linux Script Developer | prompts.chat | 91 | documentation |
| AI2sql SQL Model — Query Generator | prompts.chat | 91 | database |
| Django Unit Test Generator | prompts.chat | 91 | backend |
| Repository Analysis & Bug Fixing | prompts.chat | 91 | security |
| Ultrathinker | prompts.chat | 91 | backend |
Browse all prompts → · Browse interactively →
Data Sources & Quality
Everything AI Coding aggregates data from multiple upstream sources, then enriches, scores, and republishes the cleaned catalog.
| Type | Sources |
|---|---|
| MCP | awesome-mcp-servers · Awesome-MCP-ZH · mcp.so |
| Skills | Tier 1: anthropics/skills · Ai-Agent-Skills · antigravity-awesome-skills · ai-agents-publicTier 2: awesome-repo-configs · awesome-openclaw-skills · openclaw/skillsTier 3: catalog/skills/curated.json |
| Rules | awesome-cursorrules · rules-2.1-optimized |
| Prompts | prompts.chat · wonderful-prompts |
Quality scoring
Every entry is scored on a 0-100 composite scale:
- Coding relevance (1-5) — How directly useful for development
- Content quality (1-5) — Documentation, maintenance, completeness
- Source trust (1-5) — Upstream reputation (e.g., Anthropic Official = 5, mcp.so = 2)
- Community signals — GitHub stars, freshness (🟢 Active / 🟡 Stale / 🔴 Abandoned), installability
Each sub-directory README shows the Top 100 entries ranked by this composite score.
Pipeline
- Sync —
scripts/sync_*.pypull from upstream sources weekly - Merge —
scripts/merge_index.pydeduplicates, enriches metadata, applies governance - Evaluate — LLM + heuristic scoring for relevance, quality, and specificity
- Publish — GitHub Actions refresh the catalog, generate README tables, and update the web catalog
everything-ai-coding/
├── install.sh / install.ps1 # One-command installers
├── catalog/ # Generated catalog data
│ ├── index.json # Full merged index (4000+ entries)
│ ├── search-index.json # Lightweight search index
│ ├── mcp/ # MCP servers — index + README
│ ├── skills/ # Skills — index + README
│ ├── rules/ # Rules — index + README
│ └── prompts/ # Prompts — index + README
├── platforms/ # Per-platform skill + command definitions
├── scripts/ # Sync, merge, scoring, and generation scripts
└── .github/workflows/ # CI automation
🛠 Coding Hub — Search & Install
Everything AI Coding also ships as a CLI tool that lets you search, browse, and install resources directly from your AI coding agent.
Quick Start
Install for your platform with one command:
macOS / Linux
# Costrict CLI (run from your project root)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform costrict
# VSCode Costrict extension
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform vscode-costrict
# Claude Code
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code
# Opencode (run from your project root)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode
Windows (PowerShell)
# Costrict CLI
irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex
# Specify the platform manually if auto-detection fails
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform costrict
After installation, try a search command:
# Claude Code
/everything-ai-coding:search typescript
# Opencode / Costrict CLI / VSCode Costrict (Roo Code)
/everything-ai-coding-search typescript
You can also hand the installation off to another agent with this prompt:
You are an installation assistant. Open the following URL, read the "For Agents" section,
and follow it exactly to install Everything AI Coding for the platform you are currently running on.
Do not clone the repository. Only read this raw file:
https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/README.md
After installation, report which platform path was used and whether verification succeeded.
Platforms
Everything AI Coding supports four AI coding platforms. The resource catalog is shared, while command names and installation paths vary slightly by platform.
| Claude Code | Costrict | Opencode | VSCode Costrict (Roo Code) | |
|---|---|---|---|---|
| Search | /everything-ai-coding:search <kw> [type:mcp] |
/everything-ai-coding-search <kw> [type:mcp] |
/everything-ai-coding-search <kw> [type:mcp] |
/everything-ai-coding-search <kw> [type:mcp] |
| Browse | /everything-ai-coding:browse [category] |
/everything-ai-coding-browse [category] |
/everything-ai-coding-browse [category] |
/everything-ai-coding-browse [category] |
| Recommend | /everything-ai-coding:recommend |
/everything-ai-coding-recommend |
/everything-ai-coding-recommend |
/everything-ai-coding-recommend |
| Install | /everything-ai-coding:install <id> |
/everything-ai-coding-install <id> |
/everything-ai-coding-install <id> |
/everything-ai-coding-install <id> |
| Uninstall | /everything-ai-coding:uninstall <id> |
/everything-ai-coding-uninstall <id> |
/everything-ai-coding-uninstall <id> |
/everything-ai-coding-uninstall <id> |
| Update | /everything-ai-coding:update |
/everything-ai-coding-update |
/everything-ai-coding-update |
/everything-ai-coding-update |
| Claude Code | Costrict | VSCode Costrict | Opencode | |
|---|---|---|---|---|
| Global skill path | ~/.claude/skills/everything-ai-coding/ |
~/.costrict/skills/everything-ai-coding/ |
~/.costrict/skills/everything-ai-coding/ |
~/.opencode/skills/everything-ai-coding/ |
| Command path | same global dir | .costrict/everything-ai-coding/commands/ (project) |
~/.roo/commands/ (global) |
.opencode/command/ (project) |
| Separator | : |
- |
- |
- |
- Costrict CLI installs command files per project, so run the installer in each repository root.
- VSCode Costrict / Roo Code installs command files globally under
~/.roo/commands/. - Claude Code can load the full skill and subcommands from the global skills directory.
- Opencode installs commands per project under
.opencode/command/.
For Agents
If you are an AI agent installing Everything AI Coding automatically, follow this section exactly.
Step 1: Run the installer
The install scripts auto-detect the host platform when possible.
macOS / Linux
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash
Windows (PowerShell)
irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex
Auto-detection uses process-level environment variables that each platform injects at startup:
| Environment variable | Platform |
|---|---|
COSTRICT_CALLER=vscode |
VSCode Costrict extension |
COSTRICT_RUNNING=1 |
Costrict CLI |
CLAUDECODE=1 |
Claude Code |
OPENCODE=1 |
Opencode |
If auto-detection fails, specify the platform manually.
macOS / Linux
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform <platform>
Windows (PowerShell)
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform <platform>
Examples:
# Claude Code (macOS/Linux)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code
# Opencode (run from the project root)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode
# Claude Code (Windows)
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform claude-code
Run the platform-specific commands below if you need to download the files directly.
Costrict CLI (global skill + project commands)
mkdir -p ~/.costrict/skills/everything-ai-coding
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/costrict/skills/everything-ai-coding/SKILL.md" -o ~/.costrict/skills/everything-ai-coding/SKILL.md
mkdir -p .costrict/everything-ai-coding/commands
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/costrict/commands/everything-ai-coding/everything-ai-coding-${cmd}.md" -o .costrict/everything-ai-coding/commands/everything-ai-coding-${cmd}.md
done
VSCode Costrict extension / Roo Code (global skill + global commands)
mkdir -p ~/.costrict/skills/everything-ai-coding
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/vscode-costrict/skills/everything-ai-coding/SKILL.md" -o ~/.costrict/skills/everything-ai-coding/SKILL.md
mkdir -p ~/.roo/commands
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/vscode-costrict/commands/everything-ai-coding/everything-ai-coding-${cmd}.md" -o ~/.roo/commands/everything-ai-coding-${cmd}.md
done
Claude Code (global skill + global commands)
mkdir -p ~/.claude/skills/everything-ai-coding
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/claude-code/skills/everything-ai-coding/SKILL.md" -o ~/.claude/skills/everything-ai-coding/SKILL.md
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/claude-code/commands/everything-ai-coding/${cmd}.md" -o ~/.claude/skills/everything-ai-coding/${cmd}.md
done
Opencode (global skill + project commands)
mkdir -p ~/.opencode/skills/everything-ai-coding
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/opencode/skills/everything-ai-coding/SKILL.md" -o ~/.opencode/skills/everything-ai-coding/SKILL.md
mkdir -p .opencode/command
for cmd in search browse recommend install uninstall update; do
curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/opencode/command/everything-ai-coding-${cmd}.md" -o .opencode/command/everything-ai-coding-${cmd}.md
done
Step 2: Verify the installation
Run a search command to confirm that the commands are available:
# Costrict CLI / Opencode
/everything-ai-coding-search typescript
# VSCode Costrict extension
Send this in the chat: "Search typescript with everything-ai-coding"
# Claude Code
/everything-ai-coding:search typescript
Expected result: a Markdown table of matching resources. If the command is missing, the installation did not land in the correct platform path.
Available commands
| Command | Description |
|---|---|
search <keyword> [type:mcp|skill|rule|prompt] |
Search resources, optionally filtered by type |
browse [category] [type:...] |
Browse by category |
recommend [type:...] |
Recommend resources based on the current project stack |
install <id> |
Install a resource |
uninstall <id> |
Uninstall a resource |
update |
Pull the latest Everything AI Coding files |
Data endpoints
Search, browse, and recommend operate on a lightweight search index. Installation fetches a per-entry API document.
| Purpose | URL |
|---|---|
| Search index | https://zgsm-ai.github.io/everything-ai-coding/api/v1/search-index.json |
| Entry API | https://zgsm-ai.github.io/everything-ai-coding/api/v1/{type}/{id}.json |
| Type index | https://zgsm-ai.github.io/everything-ai-coding/api/v1/{type}/index.json |
| Full index fallback | https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/catalog/index.json |
Why Costrict?
If you like the Everything AI Coding workflow, try Costrict — our broader AI coding agent platform built for stronger automation and team workflows.
Contributing
Contributions are welcome. Open a PR against the appropriate directory under catalog/ and make sure the resource:
- is relevant to coding or AI-assisted development,
- has an accurate
source_url,description, and tags, - follows
catalog/schema.json.
If you need maintainers' context instead of quick-start instructions, see the repository wiki in docs/wiki/.
Disclaimer
Everything AI Coding is an index and installation helper for third-party open-source resources. Every MCP server, skill, rule, and prompt listed in the catalog remains the property of its original author.
This repository does not guarantee the safety, availability, accuracy, or compliance of third-party resources. Review source code and licenses before use, and open an issue if you find security or copyright problems.
Everything AI Coding is released under the MIT License.
Everything Ai Coding Reviews
Login Required
Please log in to share your review and rating for this MCP.
Similar MCP Servers like Everything Ai Coding
Explore related MCPs that share similar capabilities and solve comparable challenges
Git
Officialby modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
Zed
OfficialClientby zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
Everything
Officialby modelcontextprotocol
Model Context Protocol Servers
Time
Officialby modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
Cline
OfficialClientby cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
Context7 MCP
Officialby upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
Daytona
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.
Continue
OfficialClientby continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
GitHub MCP Server
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.