Skip to main content
Glama
minipuft

Claude Prompts MCP Server

by minipuft
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Claude Prompts MCP Server

npm version License: MIT

Hot-reloadable prompts with chains, gates, and structured reasoning for AI assistants.

Quick Start • Features • Syntax • Docs

Quick Start

Claude Code (Recommended)

# Step 1: Add marketplace (first time only)
/plugin marketplace add minipuft/minipuft-plugins

# Step 2: Install
/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

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.

User Data: Custom prompts stored in ~/.local/share/claude-prompts/ persist across updates.

User Install — Add to ~/.config/opencode/opencode.json:

{
  "mcp": {
    "claude-prompts": {
      "type": "local",
      "command": ["npx", "-y", "claude-prompts@latest"]
    }
  }
}

Development Setup — Use the opencode-prompts plugin (includes hooks):

git clone https://github.com/minipuft/opencode-prompts ~/Applications/opencode-prompts
cd ~/Applications/opencode-prompts && npm install
ln -s ~/Applications/opencode-prompts ~/.config/opencode/plugin/opencode-prompts

Then point MCP to your local server in ~/.config/opencode/opencode.json:

{
  "mcp": {
    "claude-prompts": {
      "type": "local",
      "command": ["node", "~/Applications/opencode-prompts/server/dist/index.js", "--transport=stdio"],
      "environment": { "MCP_RESOURCES_PATH": "~/Applications/opencode-prompts/server" }
    }
  }
}

User Install:

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

Development Setup — Link local source:

git clone https://github.com/minipuft/gemini-prompts ~/Applications/gemini-prompts
cd ~/Applications/gemini-prompts && npm install
gemini link .  # Links extension from current directory

To unlink: gemini unlink 'gemini-prompts'

Same tools (prompt_engine, resource_manager, system_control) with Gemini-optimized hooks.

Custom resources? See Custom Resources for MCP_RESOURCES_PATH setup.

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"]
    }
  }
}

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

Add to your MCP config file:

Client

Config Location

Cursor

~/.cursor/mcp.json

Windsurf

~/.codeium/windsurf/mcp_config.json

Zed

~/.config/zed/settings.json → mcp key

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

Restart and test: resource_manager(resource_type:"prompt", action:"list")

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 without cloning. Add MCP_RESOURCES_PATH to any MCP config:

{
  "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/.

Fine-grained overrides (optional):

Env Var

What It Overrides

MCP_RESOURCES_PATH

All resources (recommended)

MCP_PROMPTS_PATH

Just prompts

MCP_GATES_PATH

Just gates

MCP_METHODOLOGIES_PATH

Just methodologies

Note: With npx, paths resolve relative to npm cache. Always use absolute paths with MCP_RESOURCES_PATH.

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.

📊 MCP Resources

Token-efficient read-only access for discovery and context recovery:

resource://prompt/          # List all prompts (4x fewer tokens than tool call)
resource://session/         # Active chains (recover context after compaction)
resource://metrics/pipeline # System health (lean aggregates, not raw samples)

Use chainId directly: resource://session/chain-quick_decision#1 → same ID used to resume.

Configuration (in config.json):

"resources": {
  "registerWithMcp": false,           // Master switch (default: off for token efficiency)
  "prompts": { "enabled": true },     // resource://prompt/...
  "gates": { "enabled": true },       // resource://gate/...
  "methodologies": { "enabled": true }, // resource://methodology/...
  "observability": {                  // resource://session/..., resource://metrics/...
    "enabled": true,
    "sessions": true,
    "metrics": true
  },
  "logs": { "enabled": true, "maxEntries": 500, "defaultLevel": "info" }
}

Why disabled by default? Tools provide more efficient discovery:

  • resource_manager(action:"list") returns compact summary (~300 tokens)

  • Use detail:"full" when you need descriptions

  • MCP Resources bulk-loads everything (~5000+ tokens)

📜 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)

🔄 Checkpoints

Save working directory state before risky changes. Restore instantly if something breaks:

# Checkpoint before refactoring
resource_manager(resource_type:"checkpoint", action:"create", name:"pre-refactor")

# Something broke? Rollback to checkpoint
resource_manager(resource_type:"checkpoint", action:"rollback", name:"pre-refactor", confirm:true)

# List all checkpoints
resource_manager(resource_type:"checkpoint", action:"list")

Uses git stash under the hood. Pairs with verification gates for safe autonomous loops.

✅ Verification Gates (Ralph Loops)

Ground-truth validation via shell commands—Claude keeps trying until tests pass:

# You say this:
>>implement-feature :: verify:"npm test" loop:true

# Claude does this:
# 1. Implements feature
# 2. Runs npm test → FAIL
# 3. Reads error, fixes code
# 4. Runs npm test → FAIL
# 5. Tries again...
# 6. Runs npm test → PASS ✓
# You get working code.

Context Isolation: After 3 failed attempts, spawns a fresh Claude instance with session context—no context rot, fresh perspective, automatic handoff.

Preset

Max Tries

Timeout

Use Case

:fast

1

30s

Quick iteration

:full

5

5 min

CI validation

:extended

10

10 min

Large test suites

Override options: max:15 (custom attempts), timeout:120 (custom seconds).

# Custom limits for stubborn tests
>>fix-flaky-test :: verify:"npm test" :full max:8 timeout:180 loop:true

See Ralph Loops Guide for autonomous verification patterns and cost tracking.

Syntax Reference

Symbol

Name

What It Does

Example

>>

Prompt

Execute template

>>code_review

-->

Chain

Pipe to next step

step1 --> step2

*

Repeat

Run prompt N times

>>brainstorm * 5

@

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, checkpoints

system_control

Status, analytics, health checks

prompt_engine(command:"@CAGEERF >>analysis topic:'AI safety'")
resource_manager(resource_type:"prompt", action:"list")
resource_manager(resource_type:"checkpoint", action:"create", name:"backup")
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

The feedback loop: Command with operators → Parse and inject methodology/gates → Claude 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 (~4.5MB). server/dist/ is gitignored—CI builds fresh from source.

See CONTRIBUTING.md for workflow details.

License

MIT

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

Resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/minipuft/claude-prompts-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server