mcp CLAUDE.md

mcp CLAUDE.md is an instructions file for coding agents from dot-do/mcp. It costs 1,856 tokens per session, scanned A, original, MIT.

Project instructions for building an MCP server with OAuth 2.1 authentication. MCP is a standard that lets AI applications connect to tools, while OAuth handles user sign-in and access tokens.

In plain words
What is it for?
Use it when developing or reviewing the server's authentication flow, discovery documents, authorization, token, and client-registration endpoints.
Why use it?
It explains the unusual setup in which the MCP server signs users in through another provider but also issues tokens to MCP clients.

Instructions file

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 instructions/dot-do/mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/dot-do/mcp

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dot-do/mcp/claude-md.svg)](https://agentmods.dev/instructions/dot-do/mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dot-do/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dot-do/mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,856 This file is loaded in full into every session.
When invoked 1,856 The same file — it is already loaded in full.
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 $0.01856 $0.01856
Opus 5 $0.00928 $0.00928
Sonnet 5 $0.00371 $0.00371
Haiku 4.5 $0.00186 $0.00186

Measured 3d ago against content hash 29580dca5ede, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp CLAUDE.md 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 3d 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.

CLAUDE.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Project

Critical Knowledge: MCP OAuth 2.1 Authentication

This is NOT in Claude's training data - MCP OAuth 2.1 was finalized in March 2025.

Key Insight: MCP Server = Federated OAuth 2.1 Server

The MCP server itself MUST serve .well-known/oauth-authorization-server. It acts as:

  • OAuth CLIENT to upstream provider (WorkOS, GitHub, Auth0, etc.)
  • OAuth SERVER to MCP clients (Claude, ChatGPT, etc.)

The MCP server issues its OWN tokens to MCP clients after authenticating users via the upstream provider.

Required Endpoints (served by MCP server)

/.well-known/oauth-authorization-server  # RFC 8414 - Discovery
/.well-known/oauth-protected-resource    # RFC 9728 - Resource metadata
/authorize                                # Start OAuth flow
/token                                    # Token exchange
/register                                 # Dynamic client registration (RFC 7591)

Flow Diagram

MCP Client (Claude/ChatGPT)
    │
    ├─► GET /.well-known/oauth-authorization-server
    │   └── Returns: { authorization_endpoint, token_endpoint, ... }
    │
    ├─► GET /authorize?client_id=...&code_challenge=...
    │   │
    │   └──► MCP Server redirects to WorkOS/GitHub/etc
    │        │
    │        └──► User authenticates
    │             │
    │             └──► Callback to MCP server
    │                  │
    │                  └──► MCP server issues its OWN auth code
    │
    ├─► POST /token (exchange code for MCP server's tokens)
    │
    └─► Use token for MCP requests

Implementation Options

Option 1: @cloudflare/workers-oauth-provider

import { OAuthProvider } from '@cloudflare/workers-oauth-provider'

export default new OAuthProvider({
  apiRoute: "/",
  apiHandler: MyMCP.serve("/"),
  defaultHandler: WorkOSHandler,
  authorizeEndpoint: "/authorize",
  tokenEndpoint: "/token",
  clientRegistrationEndpoint: "/register",
});

Storage: KV only (hardcoded OAUTH_KV binding)

  • Client registrations: client:{clientId}
  • Grants: grant:{userId}:{grantId}
  • Tokens: token:{userId}:{grantId}:{tokenId}

Read the full file on GitHub · 246 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. 3d ago First seen · 246 lines · 1,856 tokens per session scan A 29580dca5ede

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository dot-do/mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 1,856 tokens to every session, about $0.0093 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens