mcp-configuration

mcp-configuration is a skill for Claude Code, Codex from michaelChe956/Cadence-skills. It costs 27 tokens per session (8,821 once invoked), scanned B, original, MIT.

A setup guide for MCP, a way for coding agents to connect to external tools and services. It creates and updates the project configuration used by different coding agents.

In plain words
What is it for?
Use it to create `.mcp.json`, synchronize Codex settings, preserve related project rules, and validate or merge MCP server settings.
Why use it?
It removes the need to configure each agent’s MCP connections by hand and handles differences between their configuration formats.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions subagents; names the AskUserQuestion tool; mentions Claude Code.

Part of the cadence-init plugin — 13 skills shipped together

Good fit Use it to create .mcp.json, synchronize Codex settings, preserve related project rules, and validate or merge MCP server settings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michaelche956/cadence-skills/mcp-configuration
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 michaelChe956/Cadence-skills --skill mcp-configuration
Clone the repo
git clone --depth 1 https://github.com/michaelChe956/Cadence-skills

Made for: Claude Code, Codex.

Or install cadence-init, the plugin that ships this one along with the rest of its 13 skills.

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-configuration

README.md
[![agentmods](https://agentmods.dev/badge/skills/michaelche956/cadence-skills/mcp-configuration/github.svg)](https://agentmods.dev/skills/michaelche956/cadence-skills/mcp-configuration)
Your own site
<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/mcp-configuration"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/mcp-configuration/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-configuration

Your own site · 80×15
<a href="https://agentmods.dev/skills/michaelche956/cadence-skills/mcp-configuration"><img src="https://agentmods.dev/badge/skills/michaelche956/cadence-skills/mcp-configuration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,821 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00027 $0.08821
Opus 5 $0.00014 $0.04411
Sonnet 5 $0.00005 $0.01764
Haiku 4.5 $0.00003 $0.00882

Measured 2d ago against content hash bbc724e42c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

mcp-configuration 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 2d 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 MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

> 将以下配置合并到 `.mcp.json` 的 `mcpServers` 中,`your_zhipu_api_key` 需用户自行替换
cadence-init/skills/mcp-configuration/SKILL.md · 681 lines

How it starts

The opening of the file, as written. The whole thing — 681 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP 配置

概述

配置 MCP 服务器:创建 .mcp.json 配置文件、同步 Codex .codex/config.toml。该受管文件将由随后的 rule-config 生成,此时尚不存在,跳过本步骤继续。pi 无原生 MCP,由 /pre-check 全局安装的 pi-mcp-adapter 扩展直接读取 .mcp.json(含 HTTP 类型 server),无需同步第二份配置。Kimi Code 原生读取项目根 .mcp.json(三层加载:~/.kimi-code/mcp.json<项目根>/.mcp.json<cwd>/.kimi-code/mcp.json,后者覆盖前者),本 Skill 维护的 .mcp.json 即 Kimi 的 MCP 配置来源,无需同步第二份配置。默认不需要人工交互即可完成基础 MCP 初始化。

参数模式

支持以下调用方式:

/mcp-configuration
/mcp-configuration no-interrupt
/mcp-configuration --no-interrupt
  • 命令参数包含完整 token no-interrupt--no-interrupt:进入 no-interrupt 模式。
  • 未携带上述参数:进入普通模式,完整遵循本 Skill 修改前的补齐缺失配置、同名冲突询问或跳过策略。
  • 两种模式互斥;不得把 no-interrupt 深度合并规则应用到普通模式。

no-interrupt 通用规则

  • 禁止调用 AskUserQuestionrequest_user_input 或等价用户提问工具。
  • 禁止等待用户输入、设置交互超时或通过推荐默认值继续。
  • 同名配置冲突必须按本节的确定性规则合并,不得保留冲突后跳过该 Server。
  • 写入前必须验证 JSON/TOML 结构并保留必要备份;备份、合并或验证失败时立即报错终止。
  • 失败报告不得输出 API Key、Token、Authorization Header 等真实私密值。

no-interrupt MCP 集合合并

mcp-configuration 定义的必需 Server、传输类型、命令、URL 和必要参数是权威配置;当前项目配置作为补充保留。

场景 合并动作
Skill Server 缺失 新增 Skill Server
项目额外 Server 保留项目 Server
同名 Server 的 typecommandurl 冲突 使用 Skill 值
同名 Server 的必要参数冲突 Skill 必需参数作为数组前缀,再追加不重复且不改变必需语义的项目参数
项目独有 envheadershttp_headers 或扩展字段 按键保留并合并
内容完全重复 只保留一份

Server 名称使用精确名称匹配,不进行大小写归一化。.mcp.jsonmcpServers 子项合并;.codex/config.toml[mcp_servers.<name>] 配置块合并。Codex 同步 stdio Server(有 command 字段,写 command/args/env)与 HTTP Server(有 url 字段,写 url + http_headers,即 streamable_http 传输;要求 codex-cli >= 0.44,旧版本会忽略 HTTP 块)。

no-interrupt 占位符与私密值

  • your_zhipu_api_keyyour_minimax_api_key 以及 your_*_api_key 形式的值视为占位符。
  • Skill 占位符与项目非占位值冲突时,保留项目非占位值;这是“Skill 结构权威”的唯一值级例外。
  • Skill 非占位值与项目值冲突时,使用 Skill 值。
  • 执行报告只允许记录变量名和“已保留非占位值”,不得显示、截断显示或散列输出真实值。

no-interrupt 解析失败与备份

  1. 修改现有 .mcp.json.codex/config.toml 前,先完成语法解析。
  2. 无法解析时,将原文件备份为 <原文件名>.cadence-backup-YYYYMMDDHHMMSS
  3. 只允许恢复能够作为完整 JSON Server 对象或完整 TOML Server 配置块独立解析成功的项目配置。
  4. 以 Skill 标准配置为基础重建目标文件,再按“MCP 集合合并”规则合并已恢复的完整配置块。
  5. 无法安全识别项目补充配置时立即报错,不覆盖原文件;备份仅用于恢复,不代表初始化成功。
  6. 合并完成后重新解析目标文件;验证失败时恢复备份并报错终止。

Read the full file on GitHub · 681 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 Changed · +12 lines bbc724e42c70
  2. 12d ago First seen · 669 lines · 27 tokens per session scan B 0357897ef263

Subscribe to this mod's changes

mcp-configuration is a skill published in the GitHub repository michaelChe956/Cadence-skills (11 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 8,821 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). 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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens