mcp-builder

mcp-builder is a skill for Claude Code, Codex from vudovn/ag-kit. It costs 30 tokens per session (2,063 once invoked), scanned A, original, MIT.

Guidance for building MCP (Model Context Protocol) servers and clients that let AI applications exchange tools, data, and requests.

In plain words
What is it for?
Designing protocol messages and schemas, choosing transports, handling security, negotiating capabilities, and migrating between MCP versions.
Why use it?
It helps avoid incompatible implementations by separating required protocol behavior from optional features and checking what each side supports.

Skill for Claude CodeCodex

About the project

AG Kit is a toolkit that gives Google Antigravity coding agents a structured workspace with rules, skills, specialist agents, workflows, persistent memory, orchestration, MCP guidance, and a safety hook. It is for building and operating agent workflows in Antigravity, and its catalogue entries provide parts of that workspace contract.

vudovn/ag-kit · 8,170 stars · on GitHub

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

Made for: Claude Code, Codex.

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/vudovn/ag-kit/mcp-builder.svg)](https://agentmods.dev/skills/vudovn/ag-kit/mcp-builder)
Your own site
<a href="https://agentmods.dev/skills/vudovn/ag-kit/mcp-builder"><img src="https://agentmods.dev/badge/skills/vudovn/ag-kit/mcp-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,063 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00030 $0.02063
Opus 5 $0.00015 $0.01032
Sonnet 5 $0.00006 $0.00413
Haiku 4.5 $0.00003 $0.00206

Measured 5d ago against content hash 28a677abc684, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-builder 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 5d 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.

.agents/skills/mcp-builder/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Builder

Build interoperable MCP implementations against the stable 2026-07-28 specification. Treat extensions as negotiated, opt-in capabilities rather than core protocol guarantees.


1. Stable baseline and compatibility

  • The authoritative stable baseline is MCP 2026-07-28.
  • Core requests are stateless and self-contained. Do not infer protocol version, client capabilities, identity, conversation, or task state from a transport connection or process lifetime.
  • Put cross-request state behind explicit identifiers supplied on every relevant request.
  • Negotiate the protocol version and capabilities; do not assume that a client or server implements every optional feature.
  • Preserve compatibility with earlier peers where the specification requires it, including accepting legacy resource-not-found error code -32002 while emitting -32602 for invalid parameters in the current protocol.

Core versus extensions

Layer Status Engineering rule
Base protocol, versioning, message patterns Stable core Required for every implementation
Resources, prompts, tools, elicitation Optional core features Advertise and check capabilities before use
Tasks, Skills over MCP, MCP Apps Extensions Opt-in; require explicit support from both peers
Draft or vendor extensions Experimental/vendor-specific Isolate behind adapters and feature flags

Never label an extension as stable merely because one SDK or host supports it. Check the extension's own official status and version.


2. Architecture

MCP uses JSON-RPC 2.0 between hosts, clients, and servers.

host application
  └─ MCP client / runtime adapter
       ├─ stdio transport
       └─ Streamable HTTP transport
            └─ MCP server
                 ├─ resources
                 ├─ prompts
                 └─ tools

Stateless request model

Every request must carry the protocol metadata required by the negotiated version. For 2026-07-28 this includes per-request protocol version and client capability metadata under reserved _meta keys.

Read the full file on GitHub · 206 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. 5d ago First seen · 206 lines · 30 tokens per session scan A 28a677abc684

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository vudovn/ag-kit (8,170 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 2,063 once invoked, about $0.0002 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 2026-08-30.

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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