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 skills add sigistry/marketplace --skill mcp-authorizationgit clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/skills/sigistry/marketplace/mcp-authorization)<a href="https://agentmods.dev/skills/sigistry/marketplace/mcp-authorization"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/mcp-authorization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sigistry/marketplace/mcp-authorization"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/mcp-authorization.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00115 | $0.01059 |
| Opus 5.5 | $0.00046 | $0.00424 |
| Sonnet 5.5 | $0.00023 | $0.00212 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
mcp-authorization 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Authorization
Purpose
The MCP 2026-07-28 spec aligns authorization with production OAuth 2.1 and OIDC, so a remote MCP server plugs into enterprise identity (Microsoft Entra, Okta, Auth0, Keycloak) without custom workarounds. The model is simple to state and easy to get dangerously wrong: the MCP server is an OAuth 2.1 resource server. It does not mint tokens and it does not log users in; it validates an access token on every request and serves only what that token authorizes. This skill covers correct validation and the two highest-severity anti-patterns, token passthrough and the confused deputy. (stdio/local servers do not use OAuth, skip this for them.)
The roles
| Role | Who | Responsibility |
|---|---|---|
| Authorization server (AS) | Entra / Okta / Auth0 / your IdP | authenticates the user, issues access tokens |
| Resource server (RS) | your MCP server | validates the token, enforces scope, serves tools |
| Client | Claude Code / the host app | obtains a token from the AS, sends it to the RS |
Your job is the RS. You never see the user's password; you receive a bearer access token and must prove it is valid and minted for you.
Validate every token, every request
On each request, verify (see references/token-validation.md for code):
- Signature against the AS's published JWKS (cache keys, honor rotation).
- Issuer (
iss) equals your trusted AS. - Audience (
aud) equals this MCP server's identifier. This is the line that stops the confused deputy, "a valid JWT" is not enough; it must be a token intended for you. - Expiry / not-before (
exp,nbf) within skew. - Scope covers the specific tool/action being invoked; enforce least privilege per tool.
Reject with
401(invalid/absent/expired token) or403(valid token, insufficient scope). A stateless RS validates the token on the request itself, no server session needed.
Protected Resource Metadata
Publish /.well-known/oauth-protected-resource describing this RS and pointing clients at the authorization server(s) that can issue tokens for it. This is how a 2026-07-28 client discovers where to authenticate. Returning a WWW-Authenticate header on a 401 that references this metadata lets the client start the OAuth flow automatically.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 48 lines · 115 tokens per session scan A 52c1a1738420
mcp-authorization is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed 4d ago), licensed MIT. It adds 115 tokens to every session and 1,059 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…
37signals-way
Build lean, opinionated products using the 37signals philosophy from "Getting Real", "Rework", and "Shape Up". Use when the user mentions "Getting Real", "Rework", "Shape Up", "37signals", "Basecamp method", "six-week cycles", "fixed time variable scope", "appetite vs estimates", "betting table", "breadboarding", "fat…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…