mcp-client-credentials-auth AGENTS.md

mcp-client-credentials-auth AGENTS.md is an instructions file for Codex, OpenCode from velias/mcp-client-credentials-auth. It costs 5,079 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an MCP proxy that adds client-credentials OAuth authentication when connecting to remote MCP servers. They describe the project’s structure, technologies, and architecture.

In plain words
What is it for?
Use them when modifying, reviewing, testing, or troubleshooting the proxy, especially its authentication, transport, configuration, and shutdown code.
Why use it?
They give coding agents the context needed to work consistently in this repository, including where important code lives and how the proxy is configured and tested.

Instructions file for CodexOpenCode

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/velias/mcp-client-credentials-auth/agents-md
Clone the repo
git clone --depth 1 https://github.com/velias/mcp-client-credentials-auth

Made for: Codex, OpenCode.

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-client-credentials-auth AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/velias/mcp-client-credentials-auth/agents-md.svg)](https://agentmods.dev/instructions/velias/mcp-client-credentials-auth/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/velias/mcp-client-credentials-auth/agents-md"><img src="https://agentmods.dev/badge/instructions/velias/mcp-client-credentials-auth/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,079 This file is loaded in full into every session.
When invoked 5,079 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 5.1 $0.05079 $0.05079
Opus 5 $0.02540 $0.02540
Sonnet 5 $0.01016 $0.01016
Haiku 4.5 $0.00508 $0.00508

Measured 5d ago against content hash e2dd6b309ac1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-client-credentials-auth AGENTS.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 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.

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.

AGENTS.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Overview

mcp-client-credentials-auth is a local MCP proxy that authenticates to remote OAuth-protected MCP servers using the client_credentials grant, implementing the MCP OAuth Client Credentials extension (client secrets variant). It acts as a transparent auth-injecting pipe between an MCP client and a remote MCP server. Local bind is stdio by default, or Streamable HTTP (MCP_CC_PROXY_TRANSPORT=http) for multi-session on-premises deployments.

Tech Stack

  • Runtime: Node.js >= 20
  • Language: TypeScript 6.x (strict mode, CommonJS output)
  • MCP SDK: @modelcontextprotocol/sdk (both client and server modules)
  • Validation: Zod 4 (zod/v4 for config validation, zod/v3 for SDK interop; see SDK upgrade checklist)
  • Test framework: Vitest 4
  • Linter: ESLint with typescript-eslint (flat config)

Directory Layout

src/
  index.ts                   # Entry point: config, auth ready, stdio|http branch, shutdown
  config.ts                  # MCP_CC_PROXY_* env var loading, zod validation
  errors.ts                  # Proxy error categories, formatting, client-facing McpError wrap
  logger.ts                  # Structured stderr logger (key="value", no deps)
  backoff.ts                 # Shared sleep + jittered exponential backoff
  proxy-utils.ts             # sanitizeMeta, client identity helpers, PKG_VERSION
  proxy-handle.ts            # Shared ProxyHandle type
  proxy-session.ts           # Local Server <-> remote Client session (reconnect, poll, flows)
  proxy-stdio.ts             # createStdioProxy: Phase 1 + one session + StdioServerTransport
  proxy-http.ts              # createHttpProxy: Phase 1 + Express multi-session + /health/live|/ready
  tool-filter.ts             # Optional MCP_CC_PROXY_ALLOWED_TOOLS allowlist helpers
  remote-connect.ts          # Streamable HTTP / SSE connectWithTransportFallback
  remote-mcp-discovery.ts    # Phase 1 remote MCP initialize/caps (fail-closed)
  remote-oauth-discovery.ts  # RFC 9728/8414 well-known + rediscovery compare/snapshot
  token-manager.ts           # Facade: auth mode/provider, prefetch, step-up, rediscovery API
  token-refresh.ts           # Proactive IdP token refresh timer/backoff
  scope-step-up.ts           # 403 insufficient_scope fetch workaround (SDK #2255/#1582)
test/
  config.test.ts             # Config parsing, validation, defaults, transport/listen, auditCalls
  errors.test.ts             # Error classification, 4xx URL fail-fast, mcp-client-credentials-auth [category] format
  token-manager.test.ts      # Discovery, auth modes, prefetch, refresh, step-up, rediscovery
  scope-step-up.test.ts      # Scope merge + step-up fetch wrapper
  tool-filter.test.ts        # Tool allowlist helpers (list filter + name check)
  proxy.test.ts              # Stdio E2E with in-memory MCP transports, reconnection, call audit
  proxy-advanced.test.ts     # Auth usability gating, remote error wrapping, polling
  proxy-resilience.test.ts  # Fail-closed Phase 1 startup, Phase 3 reconnect, dynamic auth
  proxy-http.test.ts        # HTTP health probes, session lifecycle, audit sessionId, no process.exit on disconnect
  logger.test.ts             # Log output formatting, levels, secret redaction

Read the full file on GitHub · 169 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 · 169 lines · 5,079 tokens per session scan A e2dd6b309ac1

Subscribe to this mod's changes

mcp-client-credentials-auth AGENTS.md is an instructions file published in the GitHub repository velias/mcp-client-credentials-auth (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 5,079 tokens to every session, about $0.0254 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

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

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

next.js AGENTS.md

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

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 · 4,469 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