api-auth

A guide for protecting MCP tools and resources with authentication and permissions. Authentication verifies who is calling; authorization controls which actions or data that caller may use, and multi-tenancy separates users or organizations.

In plain words
What is it for?
Use it to configure no-auth, JWT, or OAuth modes, require scopes on tools and resources, handle input-dependent permissions, and pass tenant identity through request state.
Why use it?
It avoids scattered manual permission checks by showing how required access scopes can be declared and enforced by the framework before a handler runs.

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/cyanheads/reference-data-mcp-server/api-auth
Any agent
npx skills add cyanheads/reference-data-mcp-server --skill api-auth
Clone the repo
git clone --depth 1 https://github.com/cyanheads/reference-data-mcp-server

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,516 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00058 $0.02516
Opus 5 $0.00029 $0.01258
Sonnet 5 $0.00012 $0.00503
Haiku 4.5 $0.00006 $0.00252

Measured 2d ago against content hash 5d676a9b6163, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-auth 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 2d 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.

Origin

This is a copy

100% identical to api-auth — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/api-auth/SKILL.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

The framework handles auth at the handler factory level — tools and resources declare required scopes declaratively, and the framework enforces them before calling the handler. No try/catch or manual scope checking required for the common case.


Inline auth (primary pattern)

Declare required scopes directly on the tool or resource definition via the auth property. The handler factory checks ctx.auth.scopes against these before calling handler.

import { tool } from '@cyanheads/mcp-ts-core';

const myTool = tool('my_tool', {
  input: z.object({ query: z.string().describe('Search query') }),
  output: z.object({ result: z.string().describe('Search result') }),
  auth: ['tool:my_tool:read'],
  async handler(input, ctx) {
    // Only reached if caller has 'tool:my_tool:read' scope
  },
});

When MCP_AUTH_MODE=none, auth checks are skipped and defaults are allowed.


Dynamic auth

For runtime-computed scopes (e.g., scopes that depend on input values like a team or resource ID), use checkScopes from @cyanheads/mcp-ts-core/auth inside the handler:

import { checkScopes } from '@cyanheads/mcp-ts-core/auth';

handler: async (input, ctx) => {
  checkScopes(ctx, [`team:${input.teamId}:write`]);
  // Continues only if scope is satisfied
},

Signature: checkScopes(ctx: Context, requiredScopes: string[]): void

Throws:

  • McpError(Forbidden) — auth is active and one or more required scopes are missing
  • McpError(Unauthorized) — auth is enabled but no auth context exists on the request
  • No-ops when MCP_AUTH_MODE=none

Auth modes

Set via MCP_AUTH_MODE environment variable.

Mode Value Behavior
Disabled none No auth enforcement. All requests allowed.
JWT jwt Local secret verification via MCP_AUTH_SECRET_KEY. Requires explicit DEV_MCP_AUTH_BYPASS=true to bypass in development.
OAuth oauth JWKS verification against an external issuer.

Read the full file on GitHub · 213 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. 2d ago First seen · 213 lines · 58 tokens per session scan A 5d676a9b6163

Subscribe to this mod's changes

api-auth is a skill published in the GitHub repository cyanheads/reference-data-mcp-server (1 stars, last pushed 8d ago), licensed Apache-2.0. It adds 58 tokens to every session and 2,516 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to api-auth, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

semantic-compression

Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…

can1357/oh-my-pi · 77 tokens

histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

synthetic-sciences/openscience · 62 tokens

pydicom

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags…

synthetic-sciences/openscience · 110 tokens

etetoolkit

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

synthetic-sciences/openscience · 46 tokens

protocolsio-integration

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io…

synthetic-sciences/openscience · 85 tokens