mcp-config-fix

mcp-config-fix is a skill for Claude Code from u2n4/ai-dev-skills. It costs 104 tokens per session (3,743 once invoked), scanned A, original, MIT.

A Windows guide for repairing Claude Desktop's MCP server configuration. MCP servers are external tools that Claude Desktop can connect to; the guide explains how a UTF-8 byte-order mark can make the configuration unreadable.

In plain words
What is it for?
It is for backing up, fixing, and managing the Claude Desktop MCP configuration on Windows.
Why use it?
It addresses cases where MCP tools disappear or the configuration is overwritten after restart.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the mcp-config-fix plugin — 1 skill shipped together

Good fit It is for backing up, fixing, and managing the Claude Desktop MCP configuration on Windows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/u2n4/ai-dev-skills/mcp-config-fix
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 u2n4/ai-dev-skills --skill mcp-config-fix
Clone the repo
git clone --depth 1 https://github.com/u2n4/ai-dev-skills

Made for: Claude Code.

Or install mcp-config-fix, the plugin that ships this one along with the rest of its 1 skill.

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-config-fix

README.md
[![agentmods](https://agentmods.dev/badge/skills/u2n4/ai-dev-skills/mcp-config-fix/github.svg)](https://agentmods.dev/skills/u2n4/ai-dev-skills/mcp-config-fix)
Your own site
<a href="https://agentmods.dev/skills/u2n4/ai-dev-skills/mcp-config-fix"><img src="https://agentmods.dev/badge/skills/u2n4/ai-dev-skills/mcp-config-fix/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-config-fix

Your own site · 80×15
<a href="https://agentmods.dev/skills/u2n4/ai-dev-skills/mcp-config-fix"><img src="https://agentmods.dev/badge/skills/u2n4/ai-dev-skills/mcp-config-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,743 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00104 $0.03743
Opus 5 $0.00052 $0.01871
Sonnet 5 $0.00021 $0.00749
Haiku 4.5 $0.00010 $0.00374

Measured 10d ago against content hash 9da2c415d118, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-config-fix scanned grade A 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Download files from the internet (`Invoke-WebRequest`, `wget`, `curl`, `Net.WebClient`)
plugins/mcp-config-fix/skills/mcp-config-fix/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Config Fix — Claude Desktop Windows

⚠️ SECURITY NOTICE

This skill modifies your Claude Desktop configuration file.

  • NEVER run commands from this skill without reading them first
  • NEVER paste API keys directly — use environment variables instead
  • ALWAYS back up your config before running any fix
  • This skill will NEVER ask you to download or run external scripts

The Problem

On Windows, Claude Desktop silently fails to load MCP servers when the config file has a UTF-8 BOM (Byte Order Mark). PowerShell's Set-Content -Encoding UTF8 adds a 3-byte BOM (EF BB BF) to the beginning of files. Claude Desktop cannot parse JSON with BOM → ignores mcpServers → overwrites the file with only preferences.

Root Cause

❌ PowerShell Set-Content -Encoding UTF8  → adds BOM → Claude Desktop ignores mcpServers
❌ Notepad "Save as UTF-8"               → adds BOM → same problem
✅ [System.IO.File]::WriteAllText()       → no BOM  → works perfectly

The Fix — ALWAYS Use This Method

Step 1: Kill Claude Desktop FIRST

IMPORTANT: Never kill processes named "Claude" generically — this will kill Claude Code too!

# Safe way — only kills Claude Desktop, NOT Claude Code
Get-Process | Where-Object {$_.ProcessName -eq "Claude Desktop" -or ($_.MainWindowTitle -like "*Claude*" -and $_.ProcessName -ne "claude")} | Stop-Process -Force -ErrorAction SilentlyContinue

Or better: Ask the user to manually quit Claude Desktop from the system tray (right-click → Quit). This is the safest approach.

Step 2: Back Up Existing Config

ALWAYS create a backup before modifying anything:

$configPath = "$env:APPDATA\Claude\claude_desktop_config.json"
if (Test-Path $configPath) {
    $backupPath = "$env:APPDATA\Claude\claude_desktop_config.backup.$(Get-Date -Format 'yyyyMMdd-HHmmss').json"
    Copy-Item $configPath $backupPath
    "Backup saved to: $backupPath"
} else {
    "No existing config found — skipping backup"
}

Read the full file on GitHub · 391 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. 10d ago First seen · 391 lines · 104 tokens per session scan A 9da2c415d118

Subscribe to this mod's changes

mcp-config-fix is a skill published in the GitHub repository u2n4/ai-dev-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 3,743 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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