Claude Prompts MCP Server

An MCP workflow server.

Craft reusable prompts with validation and reasoning guidance.
Orchestrate agentic workflows with a composable operator syntax.
Export as native skills.

Quick Start · What You Get · Compose Workflows · Run Anywhere · Docs

What your AI client gives you — and what this server adds

Is this for me?

• Use this if you write the same prompts repeatedly, run multi-step workflows, or want to share reusable prompts with a team.
• Skip if your client's built-in /commands already handle what you need, or you're looking for a no-code prompt library.
• Works with Claude Code, Claude Desktop, Cursor, OpenCode, Gemini CLI, Codex, Windsurf, and Zed. Plugin installers add hooks (chain tracking, gate enforcement, state preservation) for Claude Code, OpenCode, and Gemini CLI; other clients run MCP-only.

How to write a chain

>>review target:'src/auth/' @ReACT :: 'cite sources'
  --> security_scan :: verify:"npm test"
  ==> implementation

Read top-to-bottom:

• >>review target:'src/auth/' runs the review prompt against your auth folder.
• @ReACT overlays the ReACT reasoning framework on this step.
• :: 'cite sources' adds a gate the AI must satisfy (cite sources, or retry).
• --> security_scan :: verify:"npm test" chains to step 2, which must pass npm test before producing output.
• ==> implementation hands the final step off to a client-native agent (a subagent in Claude Code).

Validation runs between steps, not only at the end. For the full operator set including *, %, and #, see the Syntax Reference details block near the bottom.

_{Chain + gate validation in action (haiku model) — gates catch errors and guide self-correction, even on the cheapest model}

Quick Start

Claude Code (Recommended)

# Add marketplace (first time only)
/plugin marketplace add minipuft/minipuft-plugins

# Install
/plugin install claude-prompts@minipuft

# Try it
>>tech_evaluation_chain library:'zod' context:'API validation'

git clone https://github.com/minipuft/claude-prompts ~/Applications/claude-prompts
cd ~/Applications/claude-prompts/server && npm install && npm run build
claude --plugin-dir ~/Applications/claude-prompts

Claude Desktop

Option A: GitHub Release (recommended)

1. Download claude-prompts-{version}.mcpb from Releases
2. Drag into Claude Desktop Settings → MCP Servers
3. Done

The .mcpb bundle is self-contained (~5MB); no npm required.

Option B: NPX (auto-updates)

Add to your config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "claude-prompts": {
      "command": "npx",
      "args": ["-y", "claude-prompts@latest", "--client", "claude-code"]
    }
  }
}

Restart Claude Desktop and test: >>research_chain topic:'remote team policies'

# OpenCode (full hooks)
npm install -g opencode-prompts && opencode-prompts install

# Gemini CLI (partial hooks)
gemini extensions install https://github.com/minipuft/gemini-prompts

git clone https://github.com/minipuft/claude-prompts.git
cd claude-prompts/server && npm install && npm run build && npm test

Custom resources: --init=~/my-prompts scaffolds a workspace of prompts, gates, frameworks, and styles. Edit the starter templates (YAML schema), or have your AI author new ones via resource_manager. Point MCP_RESOURCES_PATH at an existing workspace if you already have one in the right shape. See Custom Resources Guide.

What You Get

Four primitives you author, version, and compose. The bundled set ships 90+ prompts across 11 categories. All hot-reloadable, all versioned with rollback.

All four are managed through the resource_manager tool. Your AI creates, edits, versions, and rolls back resources through MCP; no file editing required. Failed gate checks can retry automatically or pause for your decision (Gates Guide). Build your first primitive: Prompt Authoring Tutorial.

Compose Workflows

The basic chain syntax is in How to write a chain at the top. Two patterns extend it. Chains also support conditional branching, context threading, and agent handoffs — see Chains Lifecycle and MCP Tools Reference.

See the output — tech evaluation chain with context7 research

_{Context7 fetches live library docs mid-chain — final output is a structured assessment with sources}

Verification Loops

Ground-truth validation via shell commands. The AI keeps iterating until tests pass:

>>implement-feature :: verify:"npm test" loop:true

Implements, runs the test, reads failures, fixes, retries. Spawns a fresh context after repeated failures to avoid context rot.

For autonomous test-fix cycles with context-rot prevention: Ralph Loops Guide.

Judge Mode

Let the AI pick the right resources for the task:

%judge Help me refactor this authentication module

Analyzes available templates, reasoning frameworks, validation rules, and styles, then applies the best combination automatically. For scoring and overrides see Judge Mode Guide.

Run Anywhere

Author workflows as YAML templates. Export as native skills to your client.

# skills-sync.yaml — choose what to export
registrations:
  claude-code:
    user:
      - prompt:development/review
      - prompt:development/validate_work

npm run skills:export

The review prompt becomes a /review Claude Code skill. validate_work becomes /validate_work. Same source, native experience; no MCP call required at runtime.

Compiles to Claude Code skills, Cursor rules, OpenCode commands, and more. npm run skills:diff flags when exports drift from source. Configuration, supported clients, and drift detection: Skills Sync Guide.

With Hooks

Without hooks, you're calling the three MCP tools explicitly (the LLM constructs each call). With hooks, the operators work in conversation: >>, -->, ==>, :: feel native rather than mediated, and workflow state survives across LLM turns and context compaction.

What hooks unlock:

Hooks ship with the plugin install. Full support on Claude Code (this repo) and OpenCode; partial on Gemini CLI. Other clients get the three MCP tools but no hook-driven behaviors. Detail: hooks/README.md.

How It Works

Command with operators → server parses and injects resources (framework, gates, style) → client executes the rendered prompt and self-evaluates against the gates → router decides: next step on pass, retry on fail, return on done.

Full request lifecycle, pipeline stages, and subsystem diagrams: Architecture Overview.

Documentation

Full docs index — organized by Diátaxis quadrant (tutorials, how-to, reference, concepts):

→ docs/README.md

Quick jumps: Build your first prompt · Chains lifecycle · MCP Tools reference · Architecture overview · Troubleshooting

Contributing

cd server
npm install
npm run build        # esbuild bundles to dist/index.js
npm test             # Run test suite
npm run validate:all # Full CI validation

The build produces a self-contained bundle. server/dist/ is gitignored — CI builds fresh from source.

See CONTRIBUTING.md for workflow details.

License

MIT