consent-and-scoping

consent-and-scoping is a skill for Claude Code from RedHatProductSecurity/prodsec-skills. It costs 39 tokens per session (476 once invoked), scanned A, original, Apache-2.0.

A security guide for MCP servers, which let AI tools access services and data. It defines separate permissions for actions such as reading files or sending email and requires users to approve them explicitly.

In plain words
What is it for?
Use it when designing, building, or reviewing OAuth permissions, access scopes, and consent screens for an MCP server.
Why use it?
It prevents one broad permission from granting access to unrelated tools or actions. This reduces accidental access and confused-deputy security problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the prodsec-skills plugin — 133 skills shipped together

Good fit Use it when designing, building, or reviewing OAuth permissions, access scopes, and consent screens for an MCP server.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhatproductsecurity/prodsec-skills/consent-and-scoping
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.

Any agent
npx skills add RedHatProductSecurity/prodsec-skills --skill consent-and-scoping
Clone the repo
git clone --depth 1 https://github.com/RedHatProductSecurity/prodsec-skills

Made for: Claude Code.

Or install prodsec-skills, the plugin that ships this one along with the rest of its 133 skills.

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 consent-and-scoping

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/consent-and-scoping/github.svg)](https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/consent-and-scoping)
Your own site
<a href="https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/consent-and-scoping"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/consent-and-scoping/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.

agentmods 80×15 button for consent-and-scoping

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/consent-and-scoping"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/consent-and-scoping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 476 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00039 $0.00476
Opus 5 $0.00019 $0.00238
Sonnet 5 $0.00008 $0.00095
Haiku 4.5 $0.00004 $0.00048

Measured 12d ago against content hash 9b3c62eeb97c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

consent-and-scoping 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 12d 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.

module/skills/consent-and-scoping/SKILL.md · 56 lines

What it actually says

Security Requirement

MCP servers MUST implement granular OAuth scopes and ensure users explicitly consent to them. Scopes should map to specific tool capabilities, not broad "access everything" permissions.

Granular Scope Design

Define scopes at the tool and action level:

Scope Permission
email.send Send emails via the email tool
email.read Read emails via the email tool
files.read Read files via the filesystem tool
files.write Write files via the filesystem tool
database.query Execute read-only database queries
database.modify Execute write database operations

Avoid overly broad scopes like tools.all or admin that grant blanket access.

Users MUST explicitly consent to the scopes being requested. The consent flow should:

  1. Clearly describe what each scope allows
  2. Let users see the specific tools and actions being authorized
  3. Allow users to selectively grant or deny individual scopes
  4. Record consent decisions for audit purposes

Confused Deputy Prevention

Granular scoping prevents confused deputy attacks where an MCP server is tricked into performing unauthorized actions:

  • A tool with email.read scope cannot be manipulated to send emails
  • A tool with files.read scope cannot be used to write or delete files
  • The scope boundary acts as a hard limit regardless of what the LLM requests

Implementation Checklist

  • Define granular scopes for each tool and action (e.g., email.send, files.read)
  • Publish scopes in Protected Resource Metadata (scopes_supported)
  • Enforce scope checks on every tool invocation
  • Implement user consent flow that clearly describes each scope
  • Allow users to selectively grant or deny scopes
  • Log consent decisions for audit
  • Reject tool invocations that exceed the granted scopes
  • Review and update scopes when new tools are added
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. 12d ago First seen · 56 lines · 39 tokens per session scan A 9b3c62eeb97c

Subscribe to this mod's changes

consent-and-scoping is a skill published in the GitHub repository RedHatProductSecurity/prodsec-skills (52 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 476 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

aws-sdk-java-v2-core

Provides AWS SDK for Java 2.x client configuration, credential resolution, HTTP client tuning, timeout, retry, and testing patterns. Use when creating or hardening AWS service clients, wiring Spring Boot beans, debugging auth or region issues, or choosing sync vs async SDK usage.

giuseppe-trisciuoglio/developer-kit · 62 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens