Skip to content
Back to skills

Mcp Authoring

ASecurity

Build and integrate MCP servers and clients across modern 2026 stateless and legacy initialization-based protocol revisions.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 19, 2026
ai-agentsgo

Works with

  • cli
  • mcp

Security analysis

A100/100

Scanned September 19, 2026

npx -y skills add nafeeur/MaskShift --skill mcp-authoring --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mcp Authoring?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Mcp Authoring
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nafeeur-mcp-authoring/badge)](https://www.skillsdirectory.com/skills/nafeeur-mcp-authoring)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: mcp-authoring
description: Build and integrate MCP servers and clients across modern 2026 stateless and legacy initialization-based protocol revisions.
---

# MCP Authoring

- Implement JSON-RPC framing exactly for stdio and Streamable HTTP.
- For protocol 2026-07-28, attach protocol version, client capabilities, and client identity in every request `_meta`; use `server/discover` and no initialize session.
- For legacy servers, fall back to initialize/initialized and negotiated protocol version.
- Bound schemas, descriptions, tool outputs, timeouts, and pagination.
- Keep server connections isolated and expose tools through lazy search/activation rather than injecting every schema into model context.
- Test modern, legacy, malformed, timeout, cancellation, and reconnect behavior.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…