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'

Load plugin from local source for development:

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

Edit hooks/prompts → restart Claude Code. Edit TypeScript → rebuild first.

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'

Click the badge above for one-click install, or add manually to .vscode/mcp.json:

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

Click the badge above for one-click install, or add manually to ~/.cursor/mcp.json:

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

Option A: Plugin install (recommended — includes hooks)

npm install -g opencode-prompts
opencode-prompts install

The installer configures hooks (chain tracking, gate enforcement, state preservation), plugin registration, and MCP server. See opencode-prompts for what hooks provide.

Option B: MCP server only (manual config, no hooks)

Add to ~/.config/opencode/opencode.json:

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

You'll have the three MCP tools but no chain tracking, gate enforcement, or state preservation across compactions. To load your own prompts, add an environment key — see Custom Resources.

Option A: Extension install (recommended — includes hooks)

# 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

The extension registers the MCP server and adds hooks for >> syntax detection, chain tracking, and gate reminders. See gemini-prompts for what hooks provide.

Option B: MCP server only (manual config, no hooks)

Add to ~/.gemini/settings.json:

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

You'll have the three MCP tools but no >> syntax detection, chain tracking, or gate reminders. To load your own prompts, add an env key — see Custom Resources.

Add to your MCP config file with a --client preset for deterministic handoff guidance:

JSON-based configs (Windsurf/Zed):

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

Codex (~/.codex/config.toml):

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

Supported presets: claude-code, codex, gemini, opencode, cursor, unknown.

For complete per-client setup and limitations:

• Client Integration Guide

• Client Capabilities Reference

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

Point your MCP config to server/dist/index.js. The esbuild bundle is self-contained.

Transport options: --transport=stdio (default), --transport=streamable-http (HTTP clients).

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.

Claude Desktop / VS Code / Cursor (JSON with env):

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

OpenCode (JSON with environment):

{
  "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.).

Loaded resources, active configuration, and server health at a glance

Related MCP server: Latitude MCP Server

What You Get

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

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.

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

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.

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

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

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

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.

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.

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.

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

With Hooks

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

Route operator syntax to the right tool automatically. Track workflow progress across steps and long sessions. Enforce validation rules and step handoffs between agents.

Hooks ship with the plugin install. Available for Claude Code (full), OpenCode (full), Gemini CLI (partial). Other clients: MCP tools only.

→ hooks/README.md

Modifiers:

• %clean — No framework/gate injection

• %lean — Gates only, skip framework

• %guided — Force framework injection

• %judge — AI selects best resources

→ MCP Tools Reference for full command documentation.

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