new-mcp

new-mcp is a command for coding agents from AcKeskin/contexture. It costs 48 tokens per session (269 once invoked), scanned A, original, MIT.

An interview-driven command for scaffolding a new MCP server project. MCP is a standard way for an AI agent to call tools provided by another program or service.

In plain words
What is it for?
It creates either a TypeScript or Python server, choosing between a simple tool server and an API wrapper, then defines tools, builds the project, and registers it in the appropriate Claude configuration after confirmation.
Why use it?
It turns the server setup into confirmed choices and shows the registration change before writing files or installing dependencies.

Command

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 commands/ackeskin/contexture/new-mcp
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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/commands/ackeskin/contexture/new-mcp.svg)](https://agentmods.dev/commands/ackeskin/contexture/new-mcp)
Your own site
<a href="https://agentmods.dev/commands/ackeskin/contexture/new-mcp"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/new-mcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 269 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 $0.00048 $0.00269
Opus 5 $0.00024 $0.00134
Sonnet 5 $0.00010 $0.00054
Haiku 4.5 $0.00005 $0.00027

Measured 4d ago against content hash 66c79027b5d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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.

commands/new-mcp.md · 18 lines

What it actually says

Run the new-mcp skill for the current context.

Any text after /new-mcp is treated as a hint that biases choices but never enough to skip the interview. Examples:

  • /new-mcp — full interview from the language-choice step.
  • /new-mcp weather API in TypeScript — hint suggests TS + API wrapper; skill still confirms.
  • /new-mcp simple python calculator — hint suggests Python + simple; skill still confirms.

The skill picks a language (TypeScript or Python), a flavor (simple tool server or API wrapper), prompts for a server name and tool definitions, detects registration scope, shows a ~/.claude.json diff for confirmation, and only after y writes the project files, installs dependencies, builds, and registers the MCP server.

After writing, the skill runs the build and reports success/failure. Fail-noisy: artifacts stay on disk; the skill does not auto-revert.

See ~/.claude/skills/new-mcp/SKILL.md for the full procedure.

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 · 18 lines · 48 tokens per session scan A 66c79027b5d4

Subscribe to this mod's changes

new-mcp is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 269 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 2026-08-31.