MCP AI Agent Server
A server that bridges Cline to an AI agent system, enabling seamless interaction with AI agents through the Model Context Protocol.
MCP AI Agent Server
An MCP server that bridges Cline to an AI agent system, allowing for seamless interaction with AI agents through the Model Context Protocol.
Features
- 🚀 Send Messages: Send messages to AI agents within a session.
- 💡 Session Management: Clear sessions and start new ones.
- 🔧 Assistant Management: Get a list of available assistants and change the assistant for a session.
Quick Start
Install via npm (Recommended)
npm install -g @avi/mcp-ai-agent-server
Install via npx (No installation required)
npx @avi/mcp-ai-agent-server
Configuration
For Cline
Add to your Cline MCP settings file:
Location:
- macOS:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - Windows:
%APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - Linux:
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Configuration:
{
"mcpServers": {
"ai-agent-mcp": {
"command": "npx",
"args": ["@avi/mcp-ai-agent-server"],
"env": {
"AI_AGENT_API_KEY": "your-api-key-here",
"AI_AGENT_BASE_URL": "http://localhost:3000"
}
}
}
}
Available Tools
send_message
Send a message in a session with optional attachments.
Parameters:
messageContent(required): The message content to send.attachments(optional): An array of file attachments.
Example:
"Can you use send_message to say 'hello'?"
get_session
Get or create a session.
Parameters:
- None
Example:
"Get the current session."
clear_session
Clear the current session and start a new one.
Parameters:
- None
Example:
"Please clear the session."
get_assistants
Get a list of available assistants.
Parameters:
- None
Example:
"List the available assistants."
change_assistant
Change the assistant for a session.
Parameters:
sessionId(required): The session ID to update.newAssistantId(required): The ID of the new assistant.
Example:
"Change the assistant for the current session to 'assistant-2'."
Environment Variables
| Variable | Description | Required | Default |
|---|---|---|---|
AI_AGENT_API_KEY | API key for authentication | Yes | - |
AI_AGENT_BASE_URL | Custom API endpoint for the AI agent system | No | http://localhost:3000 |
Troubleshooting
Operation Timed Out
If you encounter an "Operation timed out" error, it means the request to the AI agent service is taking longer than the server's default internal timeout. You can resolve this by increasing the timeout value in your Cline MCP settings:
{
"mcpServers": {
"ai-agent-mcp": {
"command": "npx",
"args": ["@avi/mcp-ai-agent-server"],
"timeout": 300000, // 5 minutes
"env": {
"AI_AGENT_API_KEY": "your-api-key-here",
"AI_AGENT_BASE_URL": "http://localhost:3000"
}
}
}
}
Development
Build from source
git clone https://github.com/avi/mcp-ai-agent-server.git
cd mcp-ai-agent-server
npm install
npm run build
Testing locally
# Using MCP Inspector
npx @modelcontextprotocol/inspector ./build/index.js
# Manual testing
AI_AGENT_API_KEY=test-key node ./build/index.js
License
MIT - See LICENSE for details.
Acknowledgments
Built with the Model Context Protocol SDK
Related Servers
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
codeix
Fast semantic code search for AI agents — find symbols, references, and callers across any codebase. Pre-built index committed to git, instant queries via MCP.
Lighthouse MCP Server
Audit web performance, accessibility, and SEO using Google Lighthouse.
Lightrun
AI-powered live runtime debugging with Lightrun production context.
Windows API
An MCP server for interacting with the native Windows API, enabling control over system functions and resources.
MCP Playground
A demonstration MCP server implementation in Go featuring real-time bidirectional file communication.
MCP Tool Builder
An MCP server that allows LLMs to dynamically create new tools through MCP clients like Claude Desktop.
Pretensor
Connect your data architecture, create a knowledge graph and serve MCP tools for AI to retrieve precomputed models, connections and context.
Smithery Reference Servers
A collection of reference implementations for Model Context Protocol (MCP) servers in Typescript and Python, demonstrating MCP features and SDK usage.
CPAN Package README MCP Server
Fetch READMEs, metadata, and search for CPAN packages.
Cloudflare MCP Server Example
An example of deploying a remote MCP server on Cloudflare Workers without authentication.