new-mcp

new-mcp is a skill for Claude Code from AcKeskin/contexture. It costs 75 tokens per session (2,455 once invoked), scanned A, original, MIT.

An interview-led scaffold for building an MCP server, a small program that gives an AI tool access to functions or an external API.

In plain words
What is it for?
It helps create simple tool servers or REST API wrappers in TypeScript or Python, including registration in Claude’s configuration.
Why use it?
It turns an unclear server idea into a chosen language and server type with the required project setup.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions Claude Code.

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/ackeskin/contexture/new-mcp
Any agent
npx skills add AcKeskin/contexture --skill new-mcp
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 new-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/new-mcp.svg)](https://agentmods.dev/skills/ackeskin/contexture/new-mcp)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/new-mcp"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/new-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,455 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 5.1 $0.00075 $0.02455
Opus 5 $0.00037 $0.01228
Sonnet 5 $0.00015 $0.00491
Haiku 4.5 $0.00007 $0.00246

Measured 2d ago against content hash 06f474ff29b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

new-mcp 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (lib/claude-json-merge.js, lib/tool-codegen.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/new-mcp/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

new-mcp

Scaffold MCP (Model Context Protocol) server projects end-to-end. Two flavors: simple tool server (direct computation, no external dependencies) and API wrapper (wraps an external REST API with auth, rate limiting, error handling). Both TypeScript and Python supported.

When to run

  • User types /new-mcp (explicit trigger).
  • User says "scaffold an MCP server," "create a new MCP," "add an MCP tool server."
  • Do not auto-fire. Mode A only — every run goes through the interview.

Inputs

  1. Triggering message. Anything after /new-mcp is hint text — biases language/flavor selection but never skips the interview.
  2. Existing mcps tree. mcps/ in the repo root — used for collision check.
  3. ~/.claude.json. Read for the merge contract when registering the MCP server.

Procedure

1. Language choice

Prompt:

Which language?
  1. TypeScript (Node.js)
  2. Python

Wait for the user's choice. Determines the template set and downstream commands.

2. Flavor selection

Prompt:

What kind of MCP server?
  1. Simple tool server — direct computation, no external API calls
  2. API wrapper — wraps an external REST API with auth and error handling

Wait for the user's choice. Determines template variant and whether step 7 runs.

3. Server name

Prompt:

What should the server be called? (lowercase-with-dashes, e.g. weather-lookup, jira-bridge)

Validate: lowercase letters, digits, hyphens only. No leading/trailing hyphen, no double hyphens. Reject otherwise with the rule restated.

4. Collision check

Check mcps/<name>/ directory. If it exists:

Server '<name>' already exists at mcps/<name>/.
  (o)verwrite — delete existing directory, scaffold fresh
  (r)ename    — pick a new server name
  (a)bort     — exit without changes
Choice?
  • overwrite: warn that existing files will be replaced. Proceed.
  • rename: loop back to step 3.
  • abort: stop cleanly. No writes.

5. Server description

Read the full file on GitHub · 293 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. 2d ago First seen · 293 lines · 75 tokens per session scan A 06f474ff29b0

Subscribe to this mod's changes

new-mcp is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,455 once invoked, about $0.0004 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 2026-09-03.