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

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

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

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

Custom prompts: Use --init=~/my-prompts to create a workspace with starter templates you own. Prompts created via resource_manager are saved to your active resources directory. See Custom Resources.

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'

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

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

npm install -g opencode-prompts
opencode-prompts install

{
  "mcp": {
    "claude-prompts": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "claude-prompts@latest",
        "--transport=stdio",
        "--client=opencode"
      ]
    }
  }
}

# Enable hooks (first time only — skip if already enabled)
echo '{"hooks": {"enabled": true}}' > ~/.gemini/settings.json

# Install extension
gemini extensions install https://github.com/minipuft/gemini-prompts

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

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

[mcp_servers.claude_prompts]
command = "npx"
args = ["-y", "claude-prompts@latest", "--client=codex"]

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

Custom Resources

Use your own prompts, gates, methodologies, and styles. Two approaches depending on whether you want the bundled resources or not:

Option A: Own workspace (recommended for full control)

Create a workspace with starter templates, then point your MCP config to it:

npx -y claude-prompts@latest --init=~/my-prompts

This creates ~/my-prompts/resources/ with starter prompts you own. Set MCP_WORKSPACE or MCP_RESOURCES_PATH to use it. Prompts created via resource_manager are saved here. Your AI can update them through MCP — no manual editing needed.

Option B: Plugin install (bundled resources + hooks)

Plugin installs (Claude Code, OpenCode, Gemini) set MCP_WORKSPACE automatically and ship the bundled 90+ prompts, gates, and methodologies. Prompts created via resource_manager are saved to the plugin's resources directory.

[!IMPORTANT] MCP_RESOURCES_PATH sets the base resources directory (replaces the package default). MCP_WORKSPACE enables overlay — custom resources in your workspace are loaded alongside bundled ones. Prompts, gates, methodologies, and styles with the same ID as bundled ones take priority.

{
  "mcpServers": {
    "claude-prompts": {
      "command": "npx",
      "args": ["-y", "claude-prompts@latest"],
      "env": {
        "MCP_RESOURCES_PATH": "/path/to/your/resources"
      }
    }
  }
}

{
  "mcp": {
    "claude-prompts": {
      "type": "local",
      "command": ["npx", "-y", "claude-prompts@latest", "--transport=stdio"],
      "environment": {
        "MCP_RESOURCES_PATH": "/path/to/your/resources"
      }
    }
  }
}

See CLI Configuration for all env vars including fine-grained path overrides (MCP_PROMPTS_PATH, MCP_GATES_PATH, etc.).

See the dashboard — system status overview

_{Loaded resources, active configuration, and server health at a glance}

What You Get

Four resource types you author, version, and compose into workflows.

See the catalog — listing all available prompts

_{90 prompts across 11 categories — all hot-reloadable and versionable}

Prompt Templates

Versioned YAML with hot-reload. Edit a template, test it immediately — or ask your AI to update it through MCP.

>>code_review target:'src/auth/' language:'typescript'

Validation Rules (Gates)

Criteria the AI checks its own output against. Blocking or advisory.

:: 'no false positives' :: 'cite sources with links'

Failed checks can retry automatically or pause for your decision.

[!TIP] Define your own checks. See the Gates Guide for blocking vs advisory rules, retry behavior, and shell verification.

Reasoning Guidance (Methodologies)

Frameworks that shape how the AI thinks through a problem — not just what it outputs. 6 built-in, or create your own.

@CAGEERF    # Context → Analysis → Goals → Execution → Evaluation → Refinement
@ReACT      # Reason → Act → Observe loops
@5W1H       # Who, What, Where, When, Why, How

[!TIP] Create your own framework. See the Methodologies Guide for built-in frameworks and custom authoring.

Styles

Response formatting and tone.

#analytical    # Structured, evidence-based output
#concise       # Brief, action-focused

All resources are hot-reloadable, versioned with rollback history, and managed through the resource_manager tool.

[!TIP] Ready to build your own? Start with the Prompt Authoring Tutorial.

Compose Workflows

The operator syntax wires resources together — chain steps, add validation inline, hand off steps to agents.

>>review target:'src/auth/' @CAGEERF :: 'no false positives'
  --> security_scan :: verify:"npm test"
  --> recommendations :: 'actionable, with code'
  ==> implementation

See the chain — phases completing back-to-back

_{Phases compound reasoning across steps — each step builds on validated output from the previous one}

See the output — tech evaluation chain with context7 research

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

What happened:

1. Loaded the review template with arguments
2. Injected CAGEERF reasoning guidance
3. Added a validation rule (AI self-evaluates against it)
4. Chained output to the next step
5. Ran a shell command for ground-truth validation
6. Handed the final step off to a client-native subagent

[!TIP] Chains support conditional branching, context threading, and agent handoffs. Chains Lifecycle · MCP Tools Reference

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.

[!TIP] Autonomous test-fix cycles. See Ralph Loops for presets, timeout configuration, and context-rot prevention.

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 — applies the best combination automatically.

[!TIP] How judge mode selects resources. See Judge Mode Guide for scoring, overrides, and preview with %judge.

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.

See the export — dry-run compile + skill preview

_{Dry-run compiles YAML templates into native client skills — review before writing}

[!TIP] The Skills Sync Guide covers configuration, supported clients, and drift detection.

With Hooks

Well-composed prompts carry their own structure. Hooks keep the experience consistent across models and long sessions.

prompt_engine(command:"@CAGEERF >>analysis topic:'AI safety'")
resource_manager(resource_type:"prompt", action:"list")
system_control(action:"status")

How It Works

%%{init: {'theme': 'neutral', 'themeVariables': {'background':'#0b1224','primaryColor':'#e2e8f0','primaryBorderColor':'#1f2937','primaryTextColor':'#0f172a','lineColor':'#94a3b8','fontFamily':'"DM Sans","Segoe UI",sans-serif','fontSize':'14px','edgeLabelBackground':'#0b1224'}}}%%
flowchart TB
    classDef actor fill:#0f172a,stroke:#cbd5e1,stroke-width:1.5px,color:#f8fafc;
    classDef server fill:#111827,stroke:#fbbf24,stroke-width:1.8px,color:#f8fafc;
    classDef process fill:#e2e8f0,stroke:#1f2937,stroke-width:1.6px,color:#0f172a;
    classDef client fill:#f4d0ff,stroke:#a855f7,stroke-width:1.6px,color:#2e1065;
    classDef clientbg fill:#1a0a24,stroke:#a855f7,stroke-width:1.8px,color:#f8fafc;
    classDef decision fill:#fef3c7,stroke:#f59e0b,stroke-width:1.6px,color:#78350f;

    linkStyle default stroke:#94a3b8,stroke-width:2px

    User["1. User sends command"]:::actor
    Example[">>analyze @CAGEERF :: 'cite sources'"]:::actor
    User --> Example --> Parse

    subgraph Server["MCP Server"]
        direction TB
        Parse["2. Parse operators"]:::process
        Inject["3. Inject framework + gates"]:::process
        Render["4. Render prompt"]:::process
        Decide{"6. Route verdict"}:::decision
        Parse --> Inject --> Render
    end
    Server:::server

    subgraph Client["Claude (Client)"]
        direction TB
        Execute["5. Run prompt + check gates"]:::client
    end
    Client:::clientbg

    Render -->|"Prompt with gate criteria"| Execute
    Execute -->|"Verdict + output"| Decide

    Decide -->|"PASS → render next step"| Render
    Decide -->|"FAIL → render retry prompt"| Render
    Decide -->|"Done"| Result["7. Return to user"]:::actor

Command with operators → server parses and injects resources → client executes and self-evaluates → route: next step (pass), retry (fail), or return result (done).

Documentation

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

AGPL-3.0