Provides backend API task templates for building scalable GraphQL APIs
Built on Node.js runtime environment, requiring version 18+ for execution
Distributed and installed through the npm package manager as 'worksona-mcp-server'
Includes task templates for creating modern React components with TypeScript
Supports frontend component development with TypeScript integration
Worksona MCP Server
A comprehensive MCP (Model Context Protocol) server that integrates all Worksona agents with Claude Desktop, providing automated agent discovery, multi-agent coordination, and enterprise-level AI capabilities.
šÆ Features
Actionable Resources: Ready-to-use task templates, workflows, examples, and quick actions
Automatic Agent Discovery: Loads 100+ Worksona agents from the repository automatically
Multi-Agent Coordination: Four coordination patterns (sequential, parallel, review, executive)
Intelligent Agent Suggestions: AI-powered agent matching for requests
Task Templates: Pre-configured prompts for common development tasks
Workflow Orchestration: Multi-agent workflows for complex projects
Example Prompts: Real-world scenarios with detailed implementation guides
Quick Actions: Fast solutions for immediate needs
Memory Management: Persistent context and cross-agent memory
Enterprise Integration: Full tool access and production-ready architecture
š Quick Start
Prerequisites
Node.js 18+
Claude Desktop with MCP support
Installation
Install the MCP server globally:
npm install -g worksona-mcp-serverConfigure Claude Desktop: Add to
~/.claude-desktop/config.json
(macOS) or%APPDATA%/Claude/config.json
(Windows):{ "mcpServers": { "worksona-agents": { "command": "/usr/local/bin/worksona-mcp-server" } } }Note: No API key needed! The MCP server automatically detects it's running inside Claude Desktop and uses Claude's built-in AI processing.
Restart Claude Desktop to load the MCP server
š® Usage Examples
Attach Task Templates
Instead of writing prompts from scratch, attach task template resources for instant, professional prompts:
Browse Resources in Claude Desktop's attachment panel
Attach "š API Documentation" task template
Customize the provided prompt with your API details
Submit - Claude automatically activates the
doc-writer
agent
Attach Workflow Resources
For complex projects, attach workflow resources that coordinate multiple agents:
Attach "š Full-Stack Application" workflow
Customize the workflow prompt with your project requirements
Submit - Claude automatically uses
coordinate_team
with 4 specialists
Attach Example Prompts
Get detailed guidance for common scenarios:
Attach "š” Startup MVP Development" example
Follow the comprehensive prompt template
Get coordinated help from product, technical, and marketing specialists
Attach Quick Actions
For immediate needs:
Attach "š Quick Bug Fix" action
Fill in the bug details
Get rapid debugging from the
error-detective
agent
Traditional Tool Usage
You can still use tools directly:
Claude will use the activate_agent
tool with doc-writer
automatically.
Research Workflows
Claude will use the research_workflow
tool to deploy a team of research specialists.
š Attachable Resources
The MCP server provides 21 actionable resources organized into 4 categories:
šÆ Task Templates (6 resources)
Ready-to-use prompts for common development tasks:
š API Documentation - Comprehensive API docs with examples
š Code Review - Security, performance, and best practices analysis
ā” Database Optimization - Query and schema optimization
š Security Audit - Vulnerability assessment and compliance
šØ Frontend Component - Modern React/Vue components with TypeScript
š§ Backend API - Scalable REST/GraphQL API design
š Workflows (5 resources)
Multi-agent coordination for complex projects:
š Full-Stack Application - Complete app development pipeline
š”ļø Security Review Workflow - Multi-stage security assessment
ā” Performance Optimization - Systematic performance improvement
š Market Research - Comprehensive market analysis
š DevOps Pipeline - End-to-end CI/CD setup
š” Example Prompts (5 resources)
Real-world scenarios with detailed guidance:
š” Startup MVP Development - From idea to launch
š Legacy System Modernization - Migration strategies
š¤ AI Feature Integration - Adding AI to existing apps
š± Mobile App Development - Cross-platform mobile apps
š Data Pipeline & Analytics - Data processing systems
ā” Quick Actions (5 resources)
Fast solutions for immediate needs:
š Quick Bug Fix - Rapid debugging (15-30 min)
ā” Performance Check - Fast performance analysis (20-45 min)
š Security Scan - Quick vulnerability assessment (25-40 min)
š Code Explanation - Understand existing code (15-25 min)
š¤ Technology Decision - Expert tech advice (20-35 min)
š§ Available MCP Tools
Tool | Description | Use Case |
| Activate a single agent with expertise | Specific tasks requiring domain expertise |
| Coordinate multiple agents | Complex multi-faceted projects |
| Get AI-powered agent recommendations | When unsure which agent to use |
| Browse available agents by category | Discovering capabilities |
š Architecture
š Troubleshooting
Server Won't Start
Check Node.js version (18+ required)
Verify
agents
directory existsCheck console for error messages
Agents Not Loading
Ensure
WORKSONA_AGENTS_PATH
environment variable is set (if using custom path)Verify agent metadata.json files are valid
Check file permissions
Claude Desktop Not Connecting
Verify MCP server configuration in Claude Desktop
Restart Claude Desktop after configuration changes
Check Claude Desktop logs for connection errors
š ļø Development
Building from Source
Environment Variables
WORKSONA_AGENTS_PATH
: Path to agents directory (optional, defaults to bundled agents)NODE_ENV
: Environment (development/production)LOG_LEVEL
: Logging level (debug/info/warn/error)
Adding Custom Agents
Place agent files in
agents
directory structureFollow the standard agent format (metadata.json + agent.md)
Restart the MCP server to reload agents
š Performance
Agent Discovery: ~2-3 seconds for 100+ agents
Single Agent Execution: ~500-2000ms average
Multi-Agent Coordination: ~2-10 seconds depending on complexity
Memory Usage: ~50-100MB typical operation
š Security
Agent prompts are executed in isolated contexts
No direct file system access outside designated paths
Memory is automatically cleaned to prevent data leaks
All inputs are validated before processing
š License
MIT License - see LICENSE file for details.
š¤ Contributing
Fork the repository
Create a feature branch
Make your changes
Run tests:
npm test
Submit a pull request
š Support
Check the troubleshooting section above
Review Claude Desktop MCP documentation
Open an issue for bugs or feature requests
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
Integrates 100+ specialized AI agents with Claude Desktop, providing automated agent discovery, multi-agent coordination, and ready-to-use task templates for complex development and business workflows. Enables users to leverage enterprise-level AI capabilities through actionable resources and intelligent agent matching.