Borrowing it
Nothing to install: this file belongs to PatrickSUDO/fadacai-portfolio. 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/PatrickSUDO/fadacai-portfolio/main/.agents/skills/mcp-health/SKILL.mdgit clone --depth 1 https://github.com/PatrickSUDO/fadacai-portfolioWrote 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/patricksudo/fadacai-portfolio/mcp-health)<a href="https://agentmods.dev/skills/patricksudo/fadacai-portfolio/mcp-health"><img src="https://agentmods.dev/badge/skills/patricksudo/fadacai-portfolio/mcp-health/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/patricksudo/fadacai-portfolio/mcp-health"><img src="https://agentmods.dev/badge/skills/patricksudo/fadacai-portfolio/mcp-health.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00020 | $0.00970 |
| Opus 5.5 | $0.00008 | $0.00388 |
| Sonnet 5.5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
mcp-health 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 6d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Health Check
測試所有 MCP server 的連線狀態，快速診斷問題。
Workflow
1. 平行測試所有 MCP Server
盡可能同時呼叫以下 7 個測試，使用最簡單的工具確認連線：
| # | Server | 測試工具 | 測試呼叫 |
|---|---|---|---|
| 1 | firstrade-server | get_account_balance |
() |
| 2 | yfinance-advanced | get_stock_info |
("AAPL") |
| 3 | sec-edgar-mcp | get_company_info |
("AAPL") |
| 4 | fmp-mcp | getCompanyProfile |
("AAPL") |
| 5 | technical-mcp | get_technical_indicators |
("AAPL") |
| 6 | eodhd-mcp | get_sentiment_trend |
("AAPL.US", 7) |
| 7 | polymarket-mcp | get_trending_markets |
() |
2. 判定狀態
對每個 server 的回應判定：
- ✅ Healthy — 正常返回數據
- ⚠️ Degraded — 返回但數據不完整或響應異常慢
- ❌ Failed — 呼叫失敗或超時
3. 輸出狀態表
## MCP Server 健康檢查
| Server | 狀態 | 延遲 | 備註 |
|--------|------|------|------|
| firstrade-server | ✅ Healthy | ~Xs | 即時持倉來源 |
| yfinance-advanced | ✅ Healthy | ~Xs | — |
| sec-edgar-mcp | ✅ Healthy | ~Xs | — |
| fmp-mcp | ✅ Healthy | ~Xs | Free tier |
| technical-mcp | ✅ Healthy | ~Xs | — |
| eodhd-mcp | ❌ Failed | — | 連線失敗 |
| polymarket-mcp | ✅ Healthy | ~Xs | Demo mode |
健康: X/7 | 異常: X/7
4. 失敗時的處理
對於 ❌ Failed 的 server，顯示：
- 錯誤訊息摘要
- 手動重啟指令（僅顯示，不自動執行）：
# 手動重啟指令（請在終端機執行）：
# yfinance-advanced（uvx @0.1.2，由 Claude Code 自管 stdio subprocess）：
# → 通常重開 Claude Code session 即恢復；若需驗證版本：
# uvx [email protected] --help
# sec-edgar-mcp（uvx @1.0.8，由 Claude Code 自管）：
# → 重開 Claude Code session 即恢復
# fmp-mcp（Docker 容器，非 stdio，不由 Claude Code 管）：
docker compose -f /Users/supatrick/laptop/project/mcp-servers/fmp-mcp/compose.yaml restart
# fmp-mcp 旁路驗證（不需 /mcp reconnect，直接測 helper）：
python3 /Users/supatrick/laptop/project/fadacai-portfolio/tools/fmp_query.py getCompanyProfile --args '{"symbol":"AAPL"}'
# fmp-mcp session expired（常見）→ 用 helper 取資料，不用 reconnect：
python3 /Users/supatrick/laptop/project/fadacai-portfolio/tools/fmp_query.py getBiggestGainers
5. 建議
- 若 1-2 個 server 失敗 → 建議重啟該 server，其他 skill 可正常使用（會 fallback）
- 若 3+ 個 server 失敗 → 建議重啟 Claude Code session
- 提醒：MCP server 由 Claude Code 自動管理，通常重開 session 即可恢復
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.
- 6d ago Changed f0675a51d253
- 2mo ago First seen · 89 lines · 20 tokens per session scan A e132e9591d84
mcp-health is a skill published in the GitHub repository PatrickSUDO/fadacai-portfolio (144 stars, last pushed 7d ago), licensed MIT. It adds 20 tokens to every session and 970 once invoked, about $0.0001 per session on Opus 5.5. 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.
mcp-health compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-healthPatrickSUDO/fadacai-portfolio | Skill | 144 | 7d ago | MIT | A | 20 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |