mcp-auth-handler

mcp-auth-handler is a skill for Claude Code, Codex from MagicTurtle-s/claude-code-mcp-bridge. It costs 50 tokens per session (2,386 once invoked), scanned C, original, MIT.

A troubleshooting workflow for authentication failures when using MCP servers. MCP is a standard way for an AI assistant to connect to external tools, often requiring OAuth sign-in.

In plain words
What is it for?
Use it when authentication fails, access is unauthorized, a token expires, or an MCP server requires OAuth setup.
Why use it?
It helps identify expired or missing tokens and explains how to restore access when tools return unauthorized errors.

Skill for Claude CodeCodex

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/magicturtle-s/claude-code-mcp-bridge/mcp-auth-handler
Any agent
npx skills add MagicTurtle-s/claude-code-mcp-bridge --skill mcp-auth-handler
Clone the repo
git clone --depth 1 https://github.com/MagicTurtle-s/claude-code-mcp-bridge

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-auth-handler

README.md
[![agentmods](https://agentmods.dev/badge/skills/magicturtle-s/claude-code-mcp-bridge/mcp-auth-handler.svg)](https://agentmods.dev/skills/magicturtle-s/claude-code-mcp-bridge/mcp-auth-handler)
Your own site
<a href="https://agentmods.dev/skills/magicturtle-s/claude-code-mcp-bridge/mcp-auth-handler"><img src="https://agentmods.dev/badge/skills/magicturtle-s/claude-code-mcp-bridge/mcp-auth-handler.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,386 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00050 $0.02386
Opus 5 $0.00025 $0.01193
Sonnet 5 $0.00010 $0.00477
Haiku 4.5 $0.00005 $0.00239

Measured 5d ago against content hash 1db7136c9f01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

mcp-auth-handler scanned grade C with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.claude/.credentials.json

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/.credentials.json
.claude/skills/mcp-auth-handler/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Authentication Handler

What This Skill Does

This skill helps Claude detect and resolve MCP server authentication failures when using the Claude Code MCP Bridge. It provides step-by-step guidance for OAuth authentication and token management.

When to Use This Skill

Activate this skill when you encounter any of these scenarios:

Error Messages

  • "authentication failed"
  • "unauthorized" (401/403 HTTP errors)
  • "token expired"
  • "MCP not authenticated"
  • "Authentication required for SSE server"
  • "Token expired without refresh token"
  • "No scopes available from URL or metadata"

User Requests

  • "MCP isn't working"
  • "Can't access Asana/HubSpot/SharePoint"
  • "OAuth not working"
  • "How do I authenticate with MCPs?"

Symptoms

  • MCP tools return auth errors instead of data
  • First-time setup of new MCP server
  • Re-authentication needed after token expiry

How Authentication Works

Bridge MCP Architecture

Claude Desktop → Bridge MCP → Claude Code CLI → .credentials.json → MCP Servers

Key Points:

  1. Bridge MCP does NOT handle credentials
  2. Claude Code CLI manages all authentication
  3. Tokens stored in ~/.claude/.credentials.json
  4. OAuth flow triggered via /mcp command

Token Lifecycle

Token Type Lifespan Auto-Refresh?
Access Token ~1 hour ✅ Yes (via refresh token)
Refresh Token Days/weeks ❌ No (manual /mcp)

Step-by-Step Troubleshooting

Step 1: Identify the Problem

Check error message:

  • Does it mention "auth", "unauthorized", or "token"?
  • Which MCP server is affected? (Asana, HubSpot, SharePoint, Neo4j)
  • Is this first-time setup or re-authentication?

Example Error:

Error: The Asana MCP server needs authentication.
Authentication required for SSE server.

Step 2: Run /mcp Command

Action:

# In Claude Code CLI terminal:
/mcp

What Happens:

  1. Command detects which MCPs need authentication
  2. Browser opens for OAuth authorization
  3. User grants permissions
  4. Tokens automatically saved to .credentials.json
  5. Confirmation message appears

Read the full file on GitHub · 372 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 · 372 lines · 50 tokens per session scan C 1db7136c9f01

Subscribe to this mod's changes

mcp-auth-handler is a skill published in the GitHub repository MagicTurtle-s/claude-code-mcp-bridge (1 stars, last pushed 9mo ago), licensed MIT. It adds 50 tokens to every session and 2,386 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). 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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens