Skip to content
cccskills
FreePublished on GitHub

mcp

Health-check the connected MCP servers and scout new ones: the safe pre-flight before integration work, plus a connector finder. Read-only by default. Triggers: "/mcp", "/mcp health", "/mcp discover <need>", "which MCP servers are alive", "find an MCP for <X>".

The English summary is being prepared. Showing the original description.

Works withTelegramn8n
See how to install

Files included (1)

  • SKILL.md3.8 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

/mcp — connector health-check & discovery

🧒 When reporting to Anton end with a child-simple "In plain words" recap. (memory eli5-always)

Two jobs: (1) health — is each MCP server alive & authorized? (2) discover — is there an MCP for a need Anton has? Full rules + the Telegram landmine = memory [[mcp-health-check]].

health (READ-ONLY, safe order)

  1. In-session tool check FIRST (zero-risk) — if a server's tools are present in the session, call ONE cheap read tool to confirm auth + liveness:
    • Telegram → mcp__telegram__get_me (expect Tony / @work_acct_a).
    • WhatsApp → mcp__whatsapp__get_my_profile. n8n → mcp__n8n__n8n_health_check. Google Drive/Calendar → a list call. MongoDB → list-databases. This uses the ALREADY-RUNNING server — no second client.
  2. Only if a server's tools are ABSENT → it didn't load. Diagnose registration ($USERPROFILE/.claude.json mcpServers) + processes, then reconnect.
  3. ⚠️ TELEGRAM LANDMINE: do NOT run claude mcp list or spawn a Telethon client as a casual check — a 2nd client on the same StringSession triggers AUTH_KEY_DUPLICATED and logs the account out. Prefer in-session get_me. Use claude mcp list only when the server clearly isn't loaded.
  4. Zombie/leak watch (Windows): stdio MCPs launched via uv run/npx can orphan → prefer the direct interpreter as command; the "Telegram MCP Janitor" task (every 15 min) kills true orphans (no live claude.exe ancestor). Don't guess a hung process — verify with facts (alive? progress mtime? elapsed?).

discover

Use the registry tools: mcp__mcp-registry__suggest_connectors (for a stated need), mcp__mcp-registry__search_mcp_registry, mcp__mcp-registry__list_connectors (what's already available). Rank by: does it solve a REAL recurring need? subscription/local (free) over paid ([[prefer-included-limits-before-paid-api]])? does a stdio server risk Windows orphaning? Propose, don't auto-install — wiring a new server = Anton's call.

Safety

  • Health = read-only, run anytime (this is the standing pre-flight before Telegram/integration work).
  • Reconnecting, editing .claude.json, installing a new server = pause + confirm.

Output

Per-server 🟢/🔴 (alive + authed) + any down one with its fix command; for discover, a short ranked shortlist. Then 🧒 recap. Setup detail: [[telegram-mcp-connector]], [[whatsapp-mcp-integration]], [[n8n-stack]].

<!--kit-footer-->

Like this skill? It is part of second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

03

Free

Run an autonomous consensus round between agent peers on several machines: they negotiate a decision over a shared channel and execute it without a human relaying messages. Use when multiple machines must agree on a change. Triggers: "/03", "work it out among yourselves", "find consensus". Wakes the human only for irreversible actions or a deadlock.

The English summary is being prepared. Showing the original description.

tonydzi/second-brain-starter-kit12Updated Oct 20, 2026

1

Free

Recover a session after a hard crash (app died, machine rebooted, context lost mid-work): replay the turn-state ledger for the last requests, files and decisions, run a green/red health ping over the system map, file sync and MCP connectors, then rebuild the previous session history for pickup. Triggers: "/1", "resume after crash", "wake".

The English summary is being prepared. Showing the original description.

tonydzi/second-brain-starter-kit12Updated Oct 20, 2026

agenda

Free

Show the operator's day: today's calendar plus what needs them personally (leads due, people awaiting a reply, deadlines), pulled from Calendar and Telegram and ranked. Read-only: sends and commits nothing. Triggers: "/agenda", "what's on today", "my agenda".

The English summary is being prepared. Showing the original description.

tonydzi/second-brain-starter-kit12Updated Oct 20, 2026

Rewrite machine-written text so it reads like a busy human wrote it: cut 50-70%, break the even rhythm, drop AI-tell words and filler, keep facts and protected terms. Use before publishing any post, reply or email drafted by a model. Triggers: /ai-slop, /slop, humanize, anti-slop, make it shorter and alive.

The English summary is being prepared. Showing the original description.

tonydzi/second-brain-starter-kit12Updated Oct 20, 2026

Decision protocol for strategic work: recall the knowledge vault, run a gap analysis, emit a deep-research prompt for external tools, then synthesize the returned reports into a decision memo. Use before any new product, feature, market, pricing, GTM or architecture call, where local recall alone is not enough. Triggers: "/alfa-search-recall-deepresearch", "alpha protocol", "R+DR".

The English summary is being prepared. Showing the original description.

tonydzi/second-brain-starter-kit12Updated Oct 20, 2026

- КРЕДИТ АВТОРУ ИДЕИ: совет из комментария (TG @ClawRus / @ClawInga, комменты под постами Антона в FB, треды и issue на… Триггеры: “/alpha-credit“, “/credit“, “кто нам это посоветовал“, “запиши совет“, “поблагодари советчиков“, “кому мы должны спасибо“, “кредит автору“, “чей это был совет“, “credit the author“

The English summary is being prepared. Showing the original description.

tonydzi/second-brain-starter-kit12Updated Oct 20, 2026

See all skills by tonydzi

Report a problem with this skill