More screenshots
Works with the AI Agents you already use
π MCP OAuth & Authorization Contract Preflight
Preflight redacted MCP 2026-07-28 OAuth evidence for issuer discovery, registration, PKCE, scopes, token audience, refresh behavior, and role-specific gaps.
$19
π MCP OAuth & Authorization Contract Preflight
Example session with this skill installed
Read references/input-contract.md, then check my redacted input.json evidence packet against the pinned MCP-2026-07-28 stable profile. Run python scripts/run_preflight.py input.json --output-dir evidence-output and explain the findings and missing evidence. Do not run the Markdown schema as input, contact a live server, or handle tokens.
- Read your context and instructions
- Compiled the mcp oauth
A deterministic READY, REVIEW, BLOCK, or CANNOT_ASSESS result with stable finding codes, a complete review manifest, a human-readable report, and a SHA-256 receipt.
Connects securely to your tools. The creator never sees your data.
About this skill
MCP OAuth & Authorization Contract Preflight turns owner-supplied, redacted OAuth evidence into a deterministic local migration gate for the stable MCP 2026-07-28 profile. It checks protected-resource and authorization-server metadata alignment, exact issuer discovery, DCR application_type and issuer-bound registration, PKCE, resource indicators, token audience, step-up scope union, refresh guidance, evidence references, and declared client/server role coverage. The bundled Python helper writes stable findings, a complete review manifest, JSON and Markdown reports, and a SHA-256 receipt. It runs offline, handles no live token or credential, and returns CANNOT_ASSESS when role-relevant evidence is incomplete. READY does not prove interoperability, authorize deployment, or provide a security certification.
How to run it
Read references/input-contract.md as the schema, not as executable input. Prepare one redacted UTF-8 JSON evidence packet named input.json, then run python scripts/run_preflight.py input.json --output-dir evidence-output. Review the four output files with the responsible maintainer. Missing evidence is not a pass; keep live credentials out of the packet.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
β’ The fixed rule snapshot can become stale and must be reviewed against the current MCP specification.
β’ The package does not send OAuth requests, handle tokens, or prove server interoperability.
β’ READY is not authorization to deploy or a security certification.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 25 days ago
Permissions
File Scopes
The deterministic standard-library helper makes no network request and performs no external action.