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 Local Bridge

ASecurity

Connect local desktop tools via MCP STDIO without building a server. Use when wiring Claude Code to a local app, .mcp.json fails, Windows/WSL path mismatch, unverified extension warning. TRIGGER when: MCP local, STDIO bridge, .mcp.json, desktop app closed, path matrix Windows WSL Mac. Gatilhos PT: conectar MCP local, ponte MCP, app desktop MCP, erro de path MCP, extensão sem verificação.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsshellgit

Works with

claude codeterminalmcp

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill mcp-local-bridge --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mcp Local Bridge?

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

Security grade badge for Mcp Local Bridge
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-mcp-local-bridge/badge)](https://www.skillsdirectory.com/skills/majinmagros-mcp-local-bridge)

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

Download Zip
Files
SKILL.md
---
name: mcp-local-bridge
description: Connect local desktop tools via MCP STDIO without building a server. Use when wiring Claude Code to a local app, .mcp.json fails, Windows/WSL path mismatch, unverified extension warning. TRIGGER when: MCP local, STDIO bridge, .mcp.json, desktop app closed, path matrix Windows WSL Mac. Gatilhos PT: conectar MCP local, ponte MCP, app desktop MCP, erro de path MCP, extensão sem verificação.
---

# MCP Local Bridge

## Quando usar

- Conectar Claude Code a um app desktop local via MCP (não construir server novo).
- Erro de conexão, timeout, ou tool que não aparece.
- Projeto roda em Windows/WSL/Mac e paths quebram.
- Extensão/plugin pede instalação sem selo de verificação.
- Para CONSTRUIR um server MCP, use `mcp-server-patterns`. Este skill é só PONTE local.

## Passos

1. **Leia o skill antes das tools.** Regra mandatória: descubra comandos, limites e formato esperado antes de chamar qualquer tool do bridge.
2. **Confirme que o app desktop está aberto e logado.** Bridge local exige processo vivo. App fechado = MCP morto. Verifique versão do app e do conector.
3. **Confira o `.mcp.json` custom STDIO.** Valide: `command`, `args`, `env`, `cwd`. STDIO não tem retry de rede — erro de digitação derruba tudo. Teste o comando na mão no terminal primeiro.
4. **Aplique a matriz de paths.** Windows usa `C:\...`, WSL usa `/mnt/...`, Mac usa `/Users/...`. Converta explicitamente. Nunca chute path entre subsistemas — normalize antes.
5. **Avalie extensão sem selo.** Sem selo de verificação: instale em escopo mínimo, revise permissões (filesystem, rede, shell), prefira alternativa verificada. Registre o risco.
6. **Smoke-test ponta a ponta.** Liste tools → chame 1 leitura read-only → chame 1 escrita em sandbox. Só então libere para o fluxo real.

## Regras

- Nunca duplique `mcp-server-patterns`. Aqui não se cria server, só se conecta.
- App fechado, sem debug de JSON. Abra o app primeiro.
- Nunca misture sintaxe de path Windows/WSL/Mac no mesmo config.
- Extensão sem verificação nunca ganha acesso amplo na primeira instalação.
- Sem smoke-test verde, sem uso em tarefa real.

## Related skills

- `mcp-server-patterns` — construir server, não conectar.
- `terminal-ops` — prova de execução do smoke-test.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
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. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →