Borrowing it
Nothing to install: this file belongs to aegntic/cldcde. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/aegntic/cldcde/main/.claude/skills/mcp-universal-manager/SKILL.mdgit clone --depth 1 https://github.com/aegntic/cldcdeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aegntic/cldcde/mcp-universal-manager)<a href="https://agentmods.dev/skills/aegntic/cldcde/mcp-universal-manager"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/mcp-universal-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aegntic/cldcde/mcp-universal-manager"><img src="https://agentmods.dev/badge/skills/aegntic/cldcde/mcp-universal-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 31 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.03122 |
| Opus 5 | $0.00024 | $0.01561 |
| Sonnet 5 | $0.00010 | $0.00624 |
| Haiku 4.5 | $0.00005 | $0.00312 |
Grade A, and why
MCP Universal Manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Universal Manager
Overview
Comprehensive MCP (Model Context Protocol) server management system that automatically discovers, monitors, and manages MCP servers across multiple AI platforms with real-time health monitoring and automated troubleshooting capabilities.
Prerequisites
- Access to AI platforms (Claude Code, Factory Droid, etc.)
- MCP server configuration files or directories
- Network connectivity to target platforms
- Appropriate permissions for server management
What This Skill Does
- Auto-Discovery: Automatically finds MCP servers across platforms
- Health Monitoring: Real-time monitoring of server status and performance
- Quality Scoring: Quality assessment of MCP server implementations
- Troubleshooting: Automated diagnosis and repair of common issues
- Synchronization: Cross-platform server state synchronization
- Security Monitoring: Security audit and vulnerability scanning
Quick Start (60 seconds)
Universal Discovery
# Auto-discover all MCP servers
./scripts/discover-all.sh
# Scans and catalogs:
# - Claude Code: ~/.config/claude/claude_desktop_config.json
# - Factory Droid: ~/.factory/droids/ and repositories
# - Antigravity: ~/.antigravity/scripts/ and workflows
# - Gemini: Gemini Advanced extensions directory
# - Custom: User-defined server locations
Instant Dashboard
# Generate management dashboard
./scripts/dashboard.sh
# Real-time display shows:
# ✅ Active Servers: 12 servers online
# ⚠️ Degraded: 2 servers with performance issues
# ❌ Offline: 1 server needs attention
# 📊 Quality Score: Average 8.7/10
# 🔒 Security: All servers pass basic security scan
Configuration
Platform Configuration
Edit resources/platform-config.json:
{
"platforms": {
"claude-code": {
"config_path": "~/.config/claude/claude_desktop_config.json",
"enabled": true,
"auto_discovery": true
},
"factory-droid": {
"config_path": "~/.factory/droids/",
"repo_scan": true,
"enabled": true
},
"antigravity": {
"config_path": "~/.antigravity/scripts/",
"enabled": true
},
"gemini": {
"config_path": "~/Library/Application Support/Google/Chrome/Profile 1/Extensions/",
"enabled": false
}
},
"custom_locations": [
"/opt/mcp-servers/",
"~/projects/mcp/"
]
}
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 482 lines · 48 tokens per session scan A 921cd08d33ef
MCP Universal Manager is a skill published in the GitHub repository aegntic/cldcde (11 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 3,122 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hono-core
Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.
tauri-django-react
Agents should invoke this skill for Tauri + Django + React desktop apps, especially backend lifecycle, CORS/auth, frontend integration, mandatory light/dark theming, German/English i18n, build packaging, dual desktop/web deployment, Rust commands, and platform-specific gotchas.
project-readme
Use when creating, updating, reviewing, restructuring, or harmonizing a repository's project README from verified local evidence for user-oriented or developer/library-oriented readers.
subagent-governance
Delegation admissibility governance for a parent orchestrator. Use when deciding whether to launch, sequence, replace, or accept one or more delegated child runs while preserving role fit, plan-backed worker contracts, one-writer isolation, bounded retry safety, and reviewer finding disposition. Covers admissibility…
html-report
Creates polished self-contained HTML explanation reports for complex, multi-step topics using overview tables, evidence cards, adaptive graphs or diagrams, meaningful SVG/media, and accessible tabs for long pages. Use when the user requests a browser-readable diagnostic report, technical guide, decision analysis…
repo-explorer
Agents should invoke this skill before modifying unfamiliar codebases, answering where/how something is implemented, tracing dependencies, mapping repo structure, or planning changes. Explores a repository and returns a strict JSON handoff with key files, symbols, risks, and evidence.