Claude Role Library
An MCP server that enables users to manage, search, and apply specialized AI personas within Claude Desktop and Claude Code CLI. It features a local-first architecture with YAML-based storage for organizing curated prompts and role collections.
README
Claude Role Library
An expert role selector for Claude - seamlessly switch AI personas in Claude Code CLI and Claude Desktop.
Overview
Claude Role Library is an MCP (Model Context Protocol) server that enables users to manage and apply specialized AI roles within the Claude ecosystem. Similar in concept to OpenAI's GPT Store, it provides a local-first approach to organizing and using curated prompts.
Key Features
- Cross-platform support - Works with both Claude Code CLI and Claude Desktop via MCP
- Local-first architecture - All data stored locally, no cloud dependency
- Two-tier favorites - Global and project-level role collections
- Source tracking - Track prompt origins with sync capabilities
- YAML-based storage - Human-readable, Git-friendly configuration
Installation
From npm (Coming Soon)
# Global installation
npm install -g claude-role-library
# Or use directly with npx
npx claude-role-library
Local Development
Prerequisites: Bun v1.0 or later
# Clone the repository
git clone https://github.com/user/claude-role-library.git
cd claude-role-library
# Install dependencies
bun install
# Run the server
bun run start
# Run in development mode (with hot reload)
bun run dev
Running Tests
# Run all tests
bun test
# Run tests in watch mode
bun test --watch
# Run specific test file
bun test src/schemas/role.test.ts
MCP Configuration
After npm install (future):
{
"mcpServers": {
"claude-role-library": {
"command": "npx",
"args": ["claude-role-library"]
}
}
}
For local development:
{
"mcpServers": {
"claude-role-library": {
"command": "bun",
"args": ["run", "/path/to/claude-role-library/src/index.ts"]
}
}
}
Usage
# List all available roles
/roles list
# Search for specific roles
/roles search "code review"
# Apply a role to the current session
/roles use senior-code-reviewer
# Manage favorites
/favorites list
/favorites add senior-code-reviewer
Data Structure
~/.config/claude-role-library/
├── config.yaml # Global configuration
├── sources.yaml # External source definitions
├── favorites.yaml # Favorited roles
└── roles/ # Role definitions
└── *.yaml
{project}/.claude-role-library/
└── favorites.yaml # Project-specific favorites
Tech Stack
| Component | Technology |
|---|---|
| Language | TypeScript |
| Runtime | Bun |
| Protocol | MCP SDK |
| Storage | YAML |
| Validation | Zod |
Documentation
- Architecture - System design and component overview
- Schema - Data format specifications
- Roadmap - Development progress and planned features
Roadmap
| Phase | Status | Features |
|---|---|---|
| Phase 1 | Completed | Core role management, MCP integration |
| Phase 2 | Completed | GitHub source sync, batch import |
| Phase 3 | In Progress | AI-assisted transformation, multi-source parsers, indexing |
| Phase 4 | Planned | Community sharing, usage statistics |
Contributing
Contributions are welcome. Please review the architecture documentation before submitting changes.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.