Labsco
erophames logo

Superpower MCP

โ˜… 13

from erophames

Allows MCP execution of superpowers

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅโœ“ VerifiedFreeAdvanced setup

superpowers-mcp

An MCP server that makes superpowers skills available to any LLM that supports the Model Context Protocol.

Superpowers is a skills library for Claude Code that enforces disciplined workflows -- TDD, systematic debugging, brainstorming, planning, and more. This server exposes those skills to any MCP-compatible client: Cursor, Windsurf, Gemini, Kilo Code, Claude Desktop, or your own app.

What It Exposes

The server registers skills through all three MCP primitives:

Tools

ToolDescription
list_skillsList all available skills with descriptions and file lists
use_skillLoad a skill by name -- returns the full skill content as instructions to follow (optional guardrail enforcement)
get_skill_fileLoad a supporting file from a skill (reference docs, prompt templates, scripts)
recommend_skillsRecommend top skills for a task using semantic ranking + workflow policy boosts
compose_workflowBuild an ordered multi-skill workflow for a goal
validate_workflowValidate selected skills against required workflow guardrails
semantic_search_skillsSemantic search across SKILL.md and supporting files

Prompts

Each skill is registered as an MCP prompt named superpowers:{skill-name}. Clients that support prompt selection will show these in their UI. Selecting a prompt injects the full skill content into the conversation.

Resources

Each skill's SKILL.md and supporting files are registered as resources:

superpowers://skills/brainstorming/SKILL.md
superpowers://skills/test-driven-development/testing-anti-patterns.md
superpowers://skills/systematic-debugging/root-cause-tracing.md

A resource template superpowers://skills/{skillName}/{fileName} enables dynamic access to any file.

Available Skills

SkillWhat it does
brainstormingCollaborative design through questions, approaches, and incremental validation
writing-plansBite-sized implementation plans with exact file paths and TDD steps
executing-plansBatch execution of plans with review checkpoints between tasks
subagent-driven-developmentFresh subagent per task with two-stage code review
dispatching-parallel-agentsDistribute independent tasks to concurrent agents
test-driven-developmentRED-GREEN-REFACTOR cycle -- write failing test first, always
systematic-debugging4-phase root cause analysis: investigate before you fix
verification-before-completionRun the command, read the output, then claim the result
requesting-code-reviewDispatch code review and act on severity-categorized feedback
receiving-code-reviewTechnical rigor when receiving feedback -- verify, don't blindly agree
using-git-worktreesIsolated git worktrees for parallel feature development
finishing-a-development-branchStructured options for merge, PR, or cleanup when done
writing-skillsFramework for creating, testing, and deploying new skills
using-superpowersHow the skill system works and when to invoke skills

Development

npm install
npm run build
npm test
ScriptDescription
npm run buildCompile TypeScript
npm run devWatch mode compilation
npm testRun all 58 tests
npm run test:watchWatch mode tests
npm startRun the server

Architecture

src/
  index.ts                  Entry point, stdio transport, setup and update orchestration
  server.ts                 McpServer creation, composes all registrations
  config.ts                 Persistent configuration
  update.ts                 Daily auto-update check
  git.ts                    Git operations (clone, pull, fetch) via execFile
  cli/setup.ts              Interactive setup wizard
  skills/
    types.ts                Skill, SkillFile, SkillMetadata interfaces
    discovery.ts            Directory scanning, YAML frontmatter parsing, version resolution
  tools/register.ts         list_skills, use_skill, get_skill_file
  prompts/register.ts       One MCP prompt per skill
  resources/register.ts     Static resources per file + resource template for dynamic access

Tests