mcp: Skill for Claude Code

.claude/skills/run-mcp-servers/SKILL.md

run-mcp-servers is a skill for Claude Code from nikhilpatil79/mcp. It costs 90 tokens per session (1,219 once invoked), scanned A, original, MIT.

A workspace skill for starting and testing MCP servers, which let an AI client call tools through a standard protocol, and for opening a dashboard that displays their communication.

In plain words
What is it for?
Use it to launch the notes, database, GitHub, or Docker servers, run smoke tests, inspect tool inputs, or watch JSON-RPC messages in the dashboard.
Why use it?
It checks the servers through the same handshake and tool calls a real client uses. This can reveal configuration or connection problems that importing code or running tests may miss.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is nikhilpatil79/mcp's own configuration. It tells Claude Code how to work on mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is uv run python scripts/drive_servers.py # all four.

Reuse

Borrowing it

Nothing to install: this file belongs to nikhilpatil79/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nikhilpatil79/mcp/main/.claude/skills/run-mcp-servers/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nikhilpatil79/mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for run-mcp-servers

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikhilpatil79/mcp/run-mcp-servers/github.svg)](https://agentmods.dev/skills/nikhilpatil79/mcp/run-mcp-servers)
Your own site
<a href="https://agentmods.dev/skills/nikhilpatil79/mcp/run-mcp-servers"><img src="https://agentmods.dev/badge/skills/nikhilpatil79/mcp/run-mcp-servers/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.

agentmods 80×15 button for run-mcp-servers

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikhilpatil79/mcp/run-mcp-servers"><img src="https://agentmods.dev/badge/skills/nikhilpatil79/mcp/run-mcp-servers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,219 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.01219
Opus 5 $0.00045 $0.00609
Sonnet 5 $0.00018 $0.00244
Haiku 4.5 $0.00009 $0.00122

Measured 10d ago against content hash 42a6dd93552a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

run-mcp-servers 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 10d 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.

.claude/skills/run-mcp-servers/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running the MCP servers

An MCP server's user is a protocol client, so "running" it means completing a handshake and calling tools — not importing the module, not pytest. Drive it the way Claude Code will.

Two ways, same underlying client:

  • scripts/drive_servers.py — headless smoke test, exits non-zero on failure. Use for verification.
  • uv run mcp-lab-ui — the dashboard at http://127.0.0.1:8765. Use when the user wants to see it, or when explaining how MCP works.

The dashboard

docker compose up -d          # Postgres first, or 3 of 4 servers fail
uv run mcp-lab-ui             # http://127.0.0.1:8765

Long-running — start it in the background and tell the user the URL; do not wait on it. Servers connect asynchronously, so the page fills in over a few seconds; it polls until nothing is connecting.

Panes: servers (grouped by control model), inspector (invoke anything; shows the input schema the model receives), wire log (live JSON-RPC frames, click to expand). The tap lives in src/mcp_lab_ui/hub.py::_tap — memory streams spliced between stdio_client and ClientSession, logging each SessionMessage as it passes. Frames are genuine, not reconstructed.

It's unauthenticated and can call every tool on every connected server, including Docker writes. Localhost only — never bind it outward.

The one command

docker compose up -d                              # Postgres must be up first
uv run python scripts/drive_servers.py            # all four
uv run python scripts/drive_servers.py postgres   # just one

Exit code 0 = every configured server responded. It reads .mcp.json directly, so it tests the real config rather than a copy that can drift.

Expected output: notes 4 tools, postgres 9 tools with write refused: YES, docker 19 tools, github skipped unless a PAT is set.

write refused: NO is the one result that matters most. It means the read-only Postgres setup has regressed — treat it as a failure even though the server responded. Both layers are described in docs/SERVERS.md.

Read the full file on GitHub · 107 lines

Changes

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.

  1. 10d ago First seen · 107 lines · 90 tokens per session scan A 42a6dd93552a

Subscribe to this mod's changes

run-mcp-servers is a skill published in the GitHub repository nikhilpatil79/mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 90 tokens to every session and 1,219 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens