Claude Prompts MCP Server
Hot-reloadable prompts, structured reasoning, and chain workflows for your AI assistant.
Quick Start • What You Get • Syntax • Docs
Why
Stop copy-pasting prompts. This server turns your prompt library into a programmable engine:
Version Control — Prompts are YAML + templates in git. Track changes, review diffs.
Hot Reload — Edit a template, run it immediately. No restarts.
Structured Execution — Parses operators, injects methodology, enforces quality gates.
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
The feedback loop: You send a command with operators → Server parses and injects methodology/gates → Claude executes and self-evaluates → Server routes: next step (PASS), retry (FAIL), or return result (done).
Quick Start
Claude Code (Recommended)
Step 1: Add the plugin marketplace (first time only)
/plugin marketplace add minipuft/minipuft-plugins
Step 2: Install the plugin
/plugin install claude-prompts@minipuft
Step 3: Try it
>>tech_evaluation_chain library:'zod' context:'API validation'
The plugin adds hooks that fix common issues:
Problem | Hook Fix |
Model ignores >>analyze | Detects syntax, suggests correct MCP call |
Chain step forgotten | Injects [Chain] Step 2/5 - continue |
Gate review skipped | Reminds GATE_REVIEW: PASS|FAIL |
Raw MCP works, but models sometimes miss the syntax. The hooks catch that. → hooks/README.md
User Data: Custom prompts stored in ~/.local/share/claude-prompts/ persist across updates.
Gemini CLI
# Install directly from GitHub
gemini extensions install https://github.com/minipuft/claude-prompts-mcp
# Development Setup (Hot Reload)
# Use a symbolic link to point the extension directory directly to your source code.
# This ensures changes to hooks and prompts are reflected immediately.
rm -rf ~/.gemini/extensions/gemini-prompts
ln -s "$(pwd)" ~/.gemini/extensions/gemini-prompts
The extension provides:
MCP server with the same tools (prompt_engine, resource_manager, system_control)
GEMINI.md context file with usage documentation
Hooks enhance the experience by detecting >>prompt syntax and tracking chain state. Requires Gemini CLI v0.24.0+.
Step 1: Upgrade Gemini CLI
# Check current version
gemini --version
# Upgrade to preview (required for hooks.enabled support)
npm install -g @google/gemini-cli@0.24.0-preview.0
Step 2: Enable hooks globally
Add to ~/.gemini/settings.json:
{
"hooks": {
"enabled": true
}
}
Step 3: Verify hooks are working
gemini
# On session start, you should see hook activity in logs
# Test with: >>diagnose :: 'security-review'
See hooks/README.md for detailed hook configuration.
Works with the same prompts, gates, and methodologies as Claude Code.
Claude Desktop
Method | Install Time | Updates | Custom Prompts |
Desktop Extension | 10 seconds | Manual | Built-in config |
NPX | 30 seconds | Automatic | Via env vars |
Desktop Extension (one-click):
1. Download claude-prompts.mcpb → github.com/minipuft/claude-prompts-mcp/releases
2. Drag into Claude Desktop Settings
3. Done. Optionally set a custom prompts folder when prompted.
NPX (auto-updates):
// ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
// %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"claude-prompts": {
"command": "npx",
"args": ["-y", "claude-prompts@latest"]
}
}
}
Restart Claude Desktop. Test it:
>>research_chain topic:'remote team policies' purpose:'handbook update'
→ Returns a 4-step research workflow with methodology injection and quality gates.
Other MCP Clients
Add to your MCP config:
{
"mcpServers": {
"claude-prompts": {
"command": "npx",
"args": ["-y", "claude-prompts@latest"]
}
}
}
Test: resource_manager(resource_type:"prompt", action:"list")
git clone https://github.com/minipuft/claude-prompts-mcp.git
cd claude-prompts-mcp/server && npm install && npm run build
Then point your config to server/dist/index.js.
Transport options: --transport=stdio (default), --transport=streamable-http (recommended for HTTP).
Custom Resources
Use your own prompts without cloning:
{
"mcpServers": {
"claude-prompts": {
"command": "npx",
"args": ["-y", "claude-prompts@latest"],
"env": {
"MCP_RESOURCES_PATH": "/path/to/your/resources"
}
}
}
}
Your resources directory can contain: prompts/, gates/, methodologies/, styles/.
Override Method | Example |
All resources | MCP_RESOURCES_PATH=/path/to/resources
|
Just prompts | MCP_PROMPTS_PATH=/path/to/prompts
|
CLI flag (dev) | --prompts=/path/to/prompts
|
Priority: CLI flags > individual env vars > MCP_RESOURCES_PATH > package defaults.
See CLI Configuration for all options.
What You Get
🔥 Hot Reload
Edit prompts, test immediately. Better yet—ask Claude to fix them:
User: "The code_review prompt is too verbose"
Claude: resource_manager(action:"update", id:"code_review", ...)
User: "Test it"
Claude: prompt_engine(command:">>code_review") # Uses updated version instantly
🔗 Chains
Break complex tasks into steps with -->:
analyze code --> identify issues --> propose fixes --> generate tests
Each step's output flows to the next. Add quality gates between steps.
🧠 Frameworks
Inject structured thinking patterns:
@CAGEERF Review this architecture # Context → Analysis → Goals → Execution → Evaluation → Refinement
@ReACT Debug this error # Reason → Act → Observe loops
🛡️ Gates
Quality criteria Claude self-checks:
Summarize this :: 'under 200 words' :: 'include key statistics'
Failed gates can retry automatically or pause for your decision.
✨ Judge Selection
Let Claude pick the right tools:
%judge Help me refactor this codebase
Claude analyzes available frameworks, gates, and styles, then applies the best combination.
📜 Version History
Every update is versioned. Compare, rollback, undo:
resource_manager(action:"history", id:"code_review")
resource_manager(action:"rollback", id:"code_review", version:2, confirm:true)
Syntax Reference
Symbol | Name | What It Does | Example |
>>
| Prompt | Execute template | >>code_review
|
-->
| Chain | Pipe to next step | step1 --> step2
|
@
| Framework | Inject methodology | @CAGEERF
|
::
| Gate | Add quality criteria | :: 'cite sources'
|
%
| Modifier | Toggle behavior | %clean, %judge
|
#
| Style | Apply formatting | #analytical
|
Modifiers:
%clean — No framework/gate injection
%lean — Gates only, skip framework
%guided — Force framework injection
%judge — Claude selects best resources
Using Gates
# Inline (quick)
Research AI :: 'use recent sources' --> Summarize :: 'be concise'
# With framework
@CAGEERF Explain React hooks :: 'include examples'
# Programmatic
prompt_engine({
command: ">>code_review",
gates: [{ name: "Security", criteria: ["No hardcoded secrets"] }]
})
Severity | Behavior |
Critical/High | Must pass (blocking) |
Medium/Low | Warns, continues (advisory) |
See Gates Guide for full schema.
Configuration
Customize via server/config.json:
Section | Setting | Default | Description |
prompts
| directory
| prompts
| Prompts directory (hot-reloaded) |
frameworks
| injection.systemPrompt
| enabled | Auto-inject methodology guidance |
gates
| definitionsDirectory
| gates
| Quality gate definitions |
execution
| judge
| true
| Enable %judge resource selection |
The Three Tools
Tool | Purpose |
prompt_engine
| Execute prompts with frameworks and gates |
resource_manager
| CRUD for prompts, gates, methodologies |
system_control
| Status, analytics, health checks |
prompt_engine(command:"@CAGEERF >>analysis topic:'AI safety'")
resource_manager(resource_type:"prompt", action:"list")
system_control(action:"status")
Documentation
Contributing
cd server
npm install && npm run build
npm test
npm run validate:all # Full CI check
See CONTRIBUTING.md for details.
License
MIT
