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.
npx agentmods add instructions/velias/mcp-client-credentials-auth/agents-mdgit clone --depth 1 https://github.com/velias/mcp-client-credentials-authWrote 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.
[](https://agentmods.dev/instructions/velias/mcp-client-credentials-auth/agents-md)<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>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.
| Model | Per session | Once 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 |
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.
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/v4for config validation,zod/v3for 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
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.
- 5d ago First seen · 169 lines · 5,079 tokens per session scan A e2dd6b309ac1
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.
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.
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).
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.
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.
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.
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).