mcp-builder

mcp-builder is a skill for Claude Code, Codex from Heretyc/subagent-mcp. It costs 245 tokens per session (1,620 once invoked), scanned B, original, Apache-2.0.

A set of instructions for building and installing MCP servers. MCP is a standard way for an AI assistant to use tools and access services such as databases, APIs, or files.

In plain words
What is it for?
Creating MCP servers in Node.js or Python, defining tools and resources, configuring Claude or Codex CLI, and troubleshooting installations.
Why use it?
It provides task-specific guidance for designing, packaging, configuring, and debugging these tool connections on Windows and macOS.

Skill for Claude CodeCodex

Part of the subagent-mcp plugin — 8 skills, 1 agent, 3 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add skills/heretyc/subagent-mcp/mcp-builder
Any agent
npx skills add Heretyc/subagent-mcp --skill mcp-builder
Clone the repo
git clone --depth 1 https://github.com/Heretyc/subagent-mcp

Made for: Claude Code, Codex.

Or install subagent-mcp, the plugin that ships this one along with the rest of its 8 skills, 1 agent, 3 hooks, 1 MCP server.

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/heretyc/subagent-mcp/mcp-builder.svg)](https://agentmods.dev/skills/heretyc/subagent-mcp/mcp-builder)
Your own site
<a href="https://agentmods.dev/skills/heretyc/subagent-mcp/mcp-builder"><img src="https://agentmods.dev/badge/skills/heretyc/subagent-mcp/mcp-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 245 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,620 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00245 $0.01620
Opus 5 $0.00122 $0.00810
Sonnet 5 $0.00049 $0.00324
Haiku 4.5 $0.00024 $0.00162

Measured 4d ago against content hash fa293896d7a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

mcp-builder scanned grade B 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**Codex CLI** (`~/.codex/config.toml`):
skills/mcp-builder/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Builder

Build and ship MCP servers for Claude and Codex. Load references/retrieval-map.md first to find the right leaf doc for any task. This is generic MCP-server-building guidance for arbitrary servers; it does not apply to subagent-mcp's own no-API-key architecture.

Quick Decision Tree

Some "Load" targets below are thin indexes with a same-named sub-directory (config-claude.md, implementation-patterns.md, install-windows.md, packaging-node.md, packaging-python.md, tool-resource-prompt-schemas.md, troubleshooting.md). For these, follow the index's table of contents into references/<topic>/ for full detail : don't stop at the index. See references/retrieval-map.md for specifics.

Task Load
Understand MCP protocol / primitives protocol-spec.md
Tool / resource / prompt schemas tool-resource-prompt-schemas.md
TypeScript/Node server + npm package packaging-node.md
Python server + pip/uvx package packaging-python.md
Claude Desktop or Claude Code config config-claude.md
Codex CLI config config-codex.md
Windows install / path / registry install-windows.md
macOS install / Gatekeeper / LaunchAgent install-macos.md
Implementation patterns / security implementation-patterns.md
Debug / errors / ENOENT / tool missing troubleshooting.md
Source citations source-ledger.md

Core Rules (Always Active)

  1. stdio: never write to stdout except JSON-RPC. All logs go to stderr.
  2. Absolute paths in all config files. Never relative.
  3. Windows MSIX bug: Claude Desktop MSIX reads from %LOCALAPPDATA%\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\ not %APPDATA%\Claude\. Edit the correct file.
  4. Protocol version: Current spec is 2025-06-18. Server must echo client's version on init.
  5. inputSchema must be JSON Schema with type: "object". Missing required array = all fields optional.
  6. Secrets: use env key in config, never hardcode. Never log secrets.

Read the full file on GitHub · 142 lines

Files

What ships with it

30 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.

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. 4d ago First seen · 142 lines · 245 tokens per session scan B fa293896d7a5

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 245 tokens to every session and 1,620 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

planflow

Draft a plan and get it approved as an editable flowchart in the user's browser before executing. Use when the user asks to plan a task with PlanFlow, or wants to review, edit, or approve a plan before any code changes are made.

davejj1530/planflow-greenlight · 53 tokens

seo-strategy

Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…

cbrock84/headcount · 74 tokens

implement-factory

Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.

rsmdt/the-startup · 37 tokens

chief-strategy-officer

Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…

cbrock84/headcount · 93 tokens

scenario-planning

Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…

cbrock84/headcount · 78 tokens

ai-ml-governance

Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…

cbrock84/headcount · 83 tokens