Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Mcp Smithy

ASecurity

Use when building or fixing an MCP server's tools, resources, prompts or transport. Not for configuring an existing third-party server.

6 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentstypescriptpythonnodegit

Works with

climcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add Whq02/MercuryCLI --skill mcp-smithy --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mcp Smithy?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Mcp Smithy
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/whq02-mcp-smithy-mercurycli/badge)](https://www.skillsdirectory.com/skills/whq02-mcp-smithy-mercurycli)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: mcp-smithy
description: Use when building or fixing an MCP server's tools, resources, prompts or transport. Not for configuring an existing third-party server.
argument-hint: "<purpose> [stdio|http] [python]"
---
# MCP smithy

## Define the server
- Inspect the project's SDK and transport before changing dependencies.
- For TypeScript v2, use `@modelcontextprotocol/server` with Zod 4; read `references/typescript-v2.md`.
- For Python v2, import `MCPServer` from `mcp.server`; do not use the removed `FastMCP` import.
- Give each tool a specific verb, selection description and described input fields.
- Declare `outputSchema` for structured results; return matching `structuredContent` and readable `content`.
- Return actionable tool failures as `isError: true`; distinguish them from protocol failures.
- Set read-only, destructive and idempotent annotations accurately; treat them as hints, not authorisation.
- Use resources for addressable data, resource templates for URI families and prompts for reusable messages.

## Connect and prove
- Use stdio for host-owned processes; reserve stdout for protocol traffic and stderr for logs.
- Use Streamable HTTP for remote clients; validate Origin/Host and require authentication where appropriate.
- Keep stateless handlers stateless; retain session state only when the protocol requires it.
- Resolve `${MERCURY_SKILL_DIR}` from the supplied base directory.
- Probe initialise/list/call with `node "${MERCURY_SKILL_DIR}/scripts/mcp_probe.mjs" --call greet '{"name":"Ada"}' -- node dist/index.js`; use `--self-test` to test the helper.
- Test valid input, invalid input and handler failure; use `npx @modelcontextprotocol/inspector <command>` for interactive inspection.

## Register
- Register stdio with `mercury mcp add <name> -- node dist/index.js`.
- Register HTTP with `mercury mcp add <name> <url> --transport http --scope project`.
- Use project scope for shared `.mcp.json`; keep secrets outside committed configuration.
- Confirm connection and tools in `/mcp`; document transport, requirements and registration.

## Sources
Checked: 2026-09-15. [Specification](https://modelcontextprotocol.io/specification/), [TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk), [Python SDK](https://pypi.org/project/mcp/), [Inspector](https://www.npmjs.com/package/@modelcontextprotocol/inspector).

Attribution

Whq02Whq02
View sourceMore from Whq02 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →