Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Mcp Registry

ASecurity

MCP server registry, auto-discovery, configuration, custom server development guide

530 stars
0 votes
0 copies
1 views
Added 5/29/2026
ai-agentstypescriptpythongobashsqldockerkubernetesgitapi

Works with

claude codecliapimcp

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned 5/29/2026

$npx -y skills add vibeeval/vibecosystem --skill mcp-registry --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mcp Registry?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Mcp Registry
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vibeeval-mcp-registry/badge)](https://www.skillsdirectory.com/skills/vibeeval-mcp-registry)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: mcp-registry
description: MCP server registry, auto-discovery, configuration, custom server development guide
---

# MCP Registry & Auto-Discovery

## MCP Nedir?

Model Context Protocol (MCP) - Claude'un dis sistemlerle (DB, API, browser, dosya sistemi) iletisim kurmasini saglayan standart protokol.

## Kurulu MCP Server'lar

Kontrol: `~/.mcp.json` dosyasini oku.

```bash
# Mevcut durumu gor
cd ~/.claude && python3 scripts/mcp/registry.py status
```

## Proje Icin MCP Onerisi

```bash
# Proje dizinindeki dosyalara gore oneri al
cd ~/.claude && python3 scripts/mcp/registry.py recommend /path/to/project

# Tum registry'yi gor
cd ~/.claude && python3 scripts/mcp/registry.py list
```

## Bilinen MCP Server'lar

### Resmi (Anthropic / MCP)

| Server | Kullanim | Sinyal Dosyalari |
|--------|---------|-----------------|
| github | GitHub API (repo, issue, PR) | .github/, .git/ |
| filesystem | Dosya sistemi erisimi | * |
| postgres | PostgreSQL DB | schema.prisma, *.sql, migrations/ |
| sqlite | SQLite DB | *.db, *.sqlite |
| docker | Docker yonetimi | Dockerfile, docker-compose.yml |
| puppeteer | Browser otomasyon | playwright.config.*, cypress.config.* |
| brave-search | Web arama | - |
| chrome-devtools | Browser debug | next.config.*, vite.config.* |
| kubernetes | K8s cluster | k8s/, kustomization.yaml |

### 3rd Party (Kurulu)

| Server | Kullanim | Durum |
|--------|---------|-------|
| browser-use | AI browser otomasyon | ~/.mcp.json'da |
| codebase-memory | Codebase indexing (64 dil) | ~/bin/codebase-memory-mcp |
| notion | Notion workspace | ~/.mcp.json'da |
| crawl4ai | Web crawling | pip, crwl CLI |

## ~/.mcp.json Konfigurasyonu

```json
{
  "mcpServers": {
    "server-adi": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-X"],
      "env": {
        "API_KEY": "..."
      }
    }
  }
}
```

### Ornek: GitHub MCP Ekleme

```json
{
  "mcpServers": {
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_xxxxx"
      }
    }
  }
}
```

### Ornek: PostgreSQL MCP

```json
{
  "mcpServers": {
    "postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://user:pass@localhost:5432/db"]
    }
  }
}
```

## Ozel MCP Server Yazma

### Minimal Python MCP Server

```python
from mcp.server.fastmcp import FastMCP

mcp = FastMCP("my-server")

@mcp.tool()
def my_tool(param: str) -> str:
    """Tool aciklamasi"""
    return f"Sonuc: {param}"

@mcp.resource("resource://my-data")
def my_resource() -> str:
    """Resource aciklamasi"""
    return "data"

if __name__ == "__main__":
    mcp.run()
```

### Minimal TypeScript MCP Server

```typescript
import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const server = new Server({ name: "my-server", version: "1.0.0" }, {
  capabilities: { tools: {} }
});

server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [{
    name: "my_tool",
    description: "Tool aciklamasi",
    inputSchema: { type: "object", properties: { param: { type: "string" } } }
  }]
}));

server.setRequestHandler(CallToolRequestSchema, async (request) => ({
  content: [{ type: "text", text: `Sonuc: ${request.params.arguments?.param}` }]
}));

const transport = new StdioServerTransport();
await server.connect(transport);
```

### mcp.json'a Ekleme

```json
{
  "mcpServers": {
    "my-server": {
      "command": "python3",
      "args": ["/path/to/server.py"]
    }
  }
}
```

## MCP Debug & Troubleshooting

### Server Baslatma Testi

```bash
# Server'in calistigini dogrula
echo '{"jsonrpc":"2.0","method":"initialize","params":{"capabilities":{}},"id":1}' | npx -y @modelcontextprotocol/server-github 2>/dev/null
```

### Yaygin Sorunlar

| Sorun | Cozum |
|-------|-------|
| "spawn ENOENT" | command path'i kontrol et, npx/python3 PATH'te mi? |
| "Connection refused" | Server'i manual calistir, hata mesajini oku |
| Tool gorunmuyor | Claude Code'u restart et (MCP session basinda yuklenir) |
| Timeout | args'a timeout flag ekle, veya network kontrol et |
| Auth hatasi | env degiskenlerini kontrol et (.env degil, mcp.json'a yaz) |
| Python version uyumsuzluk | Python 3.10+ gerekli, `python3 --version` kontrol et |
| pip kurulum hatasi | `pip3 install --user --break-system-packages <paket>` |

### Loglar

```bash
# Claude Code MCP loglarini gor
ls ~/.claude/logs/mcp*.log 2>/dev/null

# Server'i verbose modda calistir
DEBUG=* npx -y @modelcontextprotocol/server-github 2>&1 | head -50
```

## Auto-Discovery Hook

`mcp-discovery.ts` hook'u session basinda otomatik calisir:
- Proje dizinindeki dosyalari tarar
- Kurulu olmayan ama faydali MCP server'lari tespit eder
- systemMessage ile oneri gosterir
- Session basina 1 kez calisir

## Registry Script

```bash
cd ~/.claude && python3 scripts/mcp/registry.py recommend .  # Oneri
cd ~/.claude && python3 scripts/mcp/registry.py status       # Kurulu
cd ~/.claude && python3 scripts/mcp/registry.py list         # Tumu
```

Attribution

vibeevalvibeeval
View sourceSee grades on GitHubMore from vibeeval →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →