mcp-builder

mcp-builder is a skill for Claude Code from sskarz/nanoclawbster. It costs 36 tokens per session (1,552 once invoked), scanned A, original, MIT.

A guide for creating and registering custom MCP servers. MCP, or Model Context Protocol, lets an agent access additional tools through a server.

In plain words
What is it for?
Use it to scaffold an MCP server, install its shared packages, write server code, and register the server for use.
Why use it?
It explains the files, dependencies, and registration steps needed to make a new tool available in this environment.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Good fit Use it to scaffold an MCP server, install its shared packages, write server code, and register the server for use.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sskarz/nanoclawbster/mcp-builder
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sskarz/nanoclawbster --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/sskarz/nanoclawbster

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 mcp-builder

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sskarz/nanoclawbster/mcp-builder"><img src="https://agentmods.dev/badge/skills/sskarz/nanoclawbster/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,552 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.01552
Opus 5 $0.00018 $0.00776
Sonnet 5 $0.00007 $0.00310
Haiku 4.5 $0.00004 $0.00155

Measured 12d ago against content hash 6aa80d83cf96, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp-builder scanned grade A with 1 finding 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 12d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { execSync } from "child_process";
container/skills/mcp-builder/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building Custom MCP Servers

MCP (Model Context Protocol) servers extend what I can do by exposing new tools. I can write, register, and use them across sessions.

File locations

  • Server code: /workspace/group/mcp-servers/<server-name>/index.js
  • Shared dependencies: /workspace/group/mcp-servers/package.json
  • Registration: /workspace/group/.mcp.json

All paths under /workspace/group/ persist across container restarts.


Step-by-step: Create and register an MCP server

1. Set up shared dependencies (first time only)

All MCP servers share a single node_modules at the mcp-servers/ root. Only do this once:

mkdir -p /workspace/group/mcp-servers
cd /workspace/group/mcp-servers
if [ ! -f package.json ]; then
  npm init -y
  # Add "type": "module" for ES module support
  node -e "const p=require('./package.json'); p.type='module'; require('fs').writeFileSync('package.json', JSON.stringify(p, null, 2)+'\n')"
  npm install @modelcontextprotocol/sdk zod
fi

2. Write the server

Create /workspace/group/mcp-servers/<name>/index.js:

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";

const server = new McpServer({ name: "<name>", version: "1.0.0" });

server.tool(
  "tool-name",
  "Description of what this tool does",
  { param: z.string().describe("A parameter") },
  async ({ param }) => ({
    content: [{ type: "text", text: `Result: ${param}` }],
  })
);

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

Node resolves imports from the shared node_modules up the directory tree — no per-server install needed.

3. Test it

echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"capabilities":{},"clientInfo":{"name":"test"},"protocolVersion":"2024-11-05"}}' | node /workspace/group/mcp-servers/<name>/index.js

Should return a JSON response without errors.

Read the full file on GitHub · 216 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. 12d ago First seen · 216 lines · 36 tokens per session scan A 6aa80d83cf96

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository sskarz/nanoclawbster (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,552 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

nemo-evaluator-sdk

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

davila7/claude-code-templates · 76 tokens

Webhooks & Idempotency Audit

Comprehensive audit of ALL webhook handlers — Stripe and POD provider (Printify/Printful). Covers signature verification, idempotency guarantees, error isolation, retry safety, database transaction consistency, and monitoring. Use when asked to audit webhooks, idempotency, event handling, or webhook security.

lroy-stack/ai-pod-store · 68 tokens

Audit Plans Limits Monetization

Comprehensive audit of the SKAPARA subscription plans, usage limits, and monetization system. Use when asked to audit pricing, plans, usage limits, free tier, premium features, Stripe subscriptions, chat/design daily limits, upsell flows, or the €9.99/month plan. Covers server-side limit enforcement, bypass…

lroy-stack/ai-pod-store · 88 tokens

stripe-projects

Provision SaaS services + sync creds via Stripe Projects.

NousResearch/hermes-agent · 15 tokens

gemini-api-agent-platform

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.

davila7/claude-code-templates · 61 tokens

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens