Agent Aggregator
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Agent Aggregator list files in /tmp and analyze any Python code"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agent Aggregator
MCP Server that aggregates tools from multiple MCP servers, acting as a proxy to provide unified access to various AI agents and tools.
šÆ Features
Multi-Agent Aggregation: Connects to multiple MCP servers simultaneously
Unified Tool Interface: Exposes all tools through a single MCP interface
AI Model Integration: Each agent can have an associated AI model via OpenRouter
Dynamic Configuration: Supports runtime configuration of connected agents
Error Handling: Robust error handling and connection management
Modern Node.js: Built with ES modules and modern JavaScript features
OpenRouter Support: Integrated support for AI models through OpenRouter API
Related MCP server: MetaMCP
š Project Structure
agent-aggregator/
āāā src/
ā āāā index.js # Main MCP server entry point
ā āāā aggregator/
ā ā āāā AgentAggregator.js # Core aggregation logic
ā ā āāā MCPConnection.js # Individual MCP server connection
ā ā āāā OpenRouterClient.js # OpenRouter API integration
ā āāā config/
ā ā āāā ConfigLoader.js # Configuration management
ā āāā mcp-servers/ # Custom MCP server implementations
ā āāā README.md # MCP servers documentation
ā āāā qwen_mcp_server.py # Qwen AI MCP server
āāā config/
ā āāā agents.json # Agent configuration file
āāā tests/
ā āāā integration.test.js # Integration tests with real services
āāā scripts/
ā āāā test-server.js # Manual server testing script
āāā docs/ # Documentationš Quick Start
Installation
# Install globally from npm
npm install -g agent-aggregator
# Or clone the repository for development
git clone https://github.com/rnd-pro/agent-aggregator.git
cd agent-aggregator
# Install dependencies
npm installQuick Start with Cursor
Add to Cursor MCP configuration (
~/.cursor/mcp.json):
{
"mcpServers": {
"agent-aggregator": {
"command": "npx",
"args": ["agent-aggregator"],
"env": {
"OPENROUTER_API_KEY": "your-openrouter-api-key",
"NODE_ENV": "production"
}
}
}
}Set your OpenRouter API key:
Get key from https://openrouter.ai/
Replace
your-openrouter-api-keywith actual key
Restart Cursor and you'll have access to 14+ tools from connected MCP servers:
Filesystem operations
Code analysis tools
AI assistance tools
And more based on your configuration
Configuration
Edit config/agents.json to configure which MCP servers to connect to:
{
"agents": [
{
"name": "filesystem",
"type": "mcp",
"enabled": true,
"description": "File system operations server",
"connection": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"],
"env": {}
},
"model": {
"provider": "openrouter",
"name": "qwen/qwen3-coder:free",
"apiKey": "${OPENROUTER_API_KEY}"
}
}
],
"aggregator": {
"timeout": 30000,
"retryAttempts": 3,
"retryDelay": 1000
},
"defaults": {
"model": {
"provider": "openrouter",
"name": "qwen/qwen3-coder:free",
"apiKey": "${OPENROUTER_API_KEY}",
"baseUrl": "https://openrouter.ai/api/v1"
}
}
}Environment Variables
Set up your OpenRouter API key:
# For current session
export OPENROUTER_API_KEY="sk-or-v1-your-actual-key-here"
# Or create .env file in project root:
echo "OPENROUTER_API_KEY=sk-or-v1-your-actual-key-here" > .env
# For permanent setup (add to ~/.bashrc or ~/.zshrc):
echo 'export OPENROUTER_API_KEY="sk-or-v1-your-actual-key-here"' >> ~/.zshrcImportant: Never commit your actual API key to version control!
Running
# Start the MCP server
npm start
# Test the server
npm run test:server
# Run integration tests
npm test
# Development mode with auto-reload
npm run devš§ Usage
As MCP Server
Add to your MCP client configuration (e.g., Cursor):
{
"mcpServers": {
"agent-aggregator": {
"command": "npx",
"args": ["agent-aggregator"]
}
}
}Supported MCP Servers
Currently configured to work with:
Filesystem:
@modelcontextprotocol/server-filesystem- File system operationsClaude Code MCP:
@kunihiros/claude-code-mcp- Claude Code wrapper
You can add any MCP server that supports the standard MCP protocol. Popular options include:
@modelcontextprotocol/server-github- GitHub API operations@modelcontextprotocol/server-memory- Memory management@modelcontextprotocol/server-fetch- HTTP requests and web fetching
š Architecture
āāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāā
ā MCP Client āāāāāā Agent Aggregator āāāāāā Filesystem ā
ā (Cursor) ā ā (This Server) ā ā MCP Server ā
āāāāāāāāāāāāāāāāāāā ā ā āāāāāāāāāāāāāāāāāāā
ā ā āāāāāāāāāāāāāāāāāāā
ā āāāāāā Qwen AI ā
ā ā ā MCP Server ā
ā ā āāāāāāāāāāāāāāāāāāā
ā ā āāāāāāāāāāāāāāāāāāā
ā āāāāāā Claude Code ā
ā ā ā MCP Server ā
ā ā āāāāāāāāāāāāāāāāāāā
ā ā āāāāāāāāāāāāāāāāāāā
ā āāāāāā OpenRouter ā
ā ā ā AI Models ā
āāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāThe Agent Aggregator:
Connects to multiple downstream MCP servers
Aggregates their tools into a unified list
Routes tool calls to the appropriate server
Provides AI model access via OpenRouter for each agent
Returns results back to the client
š¤ AI Model Integration
Each MCP server can have an associated AI model that runs via OpenRouter. The default model is qwen/qwen3-coder:free.
Custom Methods
The aggregator provides custom MCP methods for AI interactions:
custom/agents/list- List all available agents and their capabilitiescustom/model/generate- Generate text using an agent's modelcustom/model/chat- Send chat completion requestscustom/models/info- Get information about all modelscustom/status- Get detailed status of all connections
š Debugging
If you encounter issues, you can inspect the MCP server:
# Debug with MCP inspector
npx @modelcontextprotocol/inspector node src/index.jsš ļø Development
For developers who want to extend or contribute:
Adding New MCP Servers
Add server configuration to
config/agents.jsonInstall the MCP server package
Test the connection
Contributing
Fork the repository
Create a feature branch
Test your changes
Submit a pull request
š Configuration Options
Agent Configuration
{
"name": "unique-agent-name",
"type": "mcp",
"enabled": true,
"description": "Agent description",
"connection": {
"command": "command-to-run",
"args": ["--arg1", "--arg2"],
"env": {
"ENV_VAR": "value"
}
},
"model": {
"provider": "openrouter",
"name": "qwen/qwen3-coder:free",
"apiKey": "${OPENROUTER_API_KEY}"
}
}Aggregator Configuration
{
"aggregator": {
"timeout": 30000, // Connection timeout in ms
"retryAttempts": 3, // Number of retry attempts
"retryDelay": 1000, // Delay between retries in ms
"concurrentConnections": 2 // Max concurrent connections
},
"defaults": {
"model": {
"provider": "openrouter",
"name": "qwen/qwen3-coder:free",
"apiKey": "${OPENROUTER_API_KEY}",
"baseUrl": "https://openrouter.ai/api/v1"
}
}
}Available Models
The system uses OpenRouter API which supports many models:
qwen/qwen3-coder:free(default) - Free Qwen 3 Coder modelopenai/gpt-4o-mini- OpenAI GPT-4o Minianthropic/claude-3.5-sonnet- Claude 3.5 Sonnetmeta-llama/llama-3.1-8b-instruct:free- Free Llama modelAnd many more - see OpenRouter Models
## š Troubleshooting
### Common Issues
1. **"Could not attach to MCP server"**
- Check that the MCP server package is installed
- Verify the command and arguments in configuration
- Ensure the server supports the MCP protocol
2. **"Connection timeout"**
- Increase timeout in aggregator configuration
- Check that the MCP server starts properly
- Verify network connectivity
3. **"Tool not found"**
- Ensure the downstream MCP server is connected
- Check tool name prefixing (format: `agent-name__tool-name`)
- Verify the tool exists in the downstream server
4. **"OpenRouter API error"**
- Verify your OPENROUTER_API_KEY is set correctly
- Check that you have credits/access to the specified model
- Ensure the model name is correct (e.g., `qwen/qwen3-coder:free`)
5. **"No AI model configured"**
- Add a `model` section to your agent configuration
- Ensure the model configuration includes provider, name, and apiKey
- Check that environment variables are properly expanded
### Debug Mode
Enable debug logging by setting environment variables:
```bash
DEBUG=1 npm startš¤ Contributing
Follow the established code style
Add tests for new functionality
Update documentation
Test with real MCP servers
š Links
npm Package - Install from npm registry
GitHub Repository - Source code and issues
OpenRouter API - Get your API key for AI models
š License
MIT License
Available Tools
10 toolsai-tools__analyze_projectB
[AI Code Analysis] Analyzes project structure and provides insights
Inputs: project_description (required), focus.
ai-tools__edit_codeC
[AI Code Analysis] Edits the given code based on instructions
Inputs: code (required), instructions (required).
ai-tools__explain_codeB
[AI Code Analysis] Provides detailed explanation of the given code
Inputs: code (required), context.
ai-tools__fix_codeC
[AI Code Analysis] Fixes bugs or issues in the given code
Inputs: code (required), issue_description (required).
ai-tools__review_codeA
[AI Code Analysis] Reviews the given code for quality and best practices
Inputs: code (required), focus_areas.
ai-tools__simulate_commandC
[AI Code Analysis] Simulates the execution of a given command
Inputs: command (required), input.
ai-tools__test_codeB
[AI Code Analysis] Generates tests for the given code
Inputs: code (required), test_framework.
filter__getA
[Filter Management] Get current tool filter configuration
Inputs: no named parameters.
filter__resetA
[Filter Management] Reset tool filter to show all available tools
Inputs: no named parameters.
filter__updateC
[Filter Management] Update tool visibility filter - control which tools are visible to AI
Inputs: excludeServers, excludePatterns, includePatterns.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 10 tools
The three filter tools are clearly distinct, and the AI code tools have distinct actions (explain, review, fix, edit, test, simulate, analyze). Some overlap exists between fix_code and edit_code, but descriptions clarify the difference.
All tools follow a consistent domain__action pattern using double underscores, but the action part is not uniformly verb_noun (e.g. filter__get vs ai-tools__explain_code). This is a minor inconsistency that does not impede readability.
Ten tools is well-scoped for an aggregator with two functional areas: filter management and AI code analysis. Each tool seems to serve a distinct purpose without redundancy.
Filter management covers get/update/reset completely, and AI code analysis covers explain, review, fix, edit, test, simulate, and project analysis. There are no obvious dead ends or missing core operations for the stated domains.
Maintenance
Related MCP Connectors
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP federation gateway: route, govern and observe agent tools across clouds and MCP servers.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAggregates multiple MCP servers and custom Python tools behind a single endpoint, with intelligent context and tool discovery for AI agents.-

MetaMCPofficial
AlicenseAqualityBmaintenanceAggregates multiple MCP servers into a single interface, reducing token overhead and simplifying tool management for LLMs.680 npm18Apache 2.0- FlicenseNot gradedqualityAmaintenanceEnables LLMs to dynamically search for, add, configure, enable/disable, and aggregate tools from multiple MCP servers at runtime, with persistent configuration and proxying.-
- FlicenseNot gradedqualityAmaintenanceEnables LLMs to manage and proxy multiple MCP servers, dynamically extending capabilities by adding, configuring, enabling, disabling, and aggregating their tools through a unified interface.-