Uses .env file for managing API keys and environment configuration
Built on Gradio's MCP server capabilities for creating a multi-agent architecture with interconnected agent services and a web interface
Uses Nebius (OpenAI-compatible) models for text processing, summarization, and question enhancement
Requires Python 3.12+ as the core runtime environment for the MCP server implementation
title: ShallowCodeResearch emoji: 📉 colorFrom: red colorTo: pink sdk: gradio sdk_version: 5.33.1 app_file: app.py pinned: false short_description: Coding research assistant that generates code and tests it tags:
mcp
multi-agent
research
code-generation
ai-assistant
gradio
python
web-search
llm
modal
mcp-server-track python_version: '3.12'
Shallow Research Code Assistant - Multi-Agent AI Code Assistant
Technologies Used
This is part of the MCP track for the Hackathon (with a smidge of Agents)
Gradio for the UI and MCP logic
Modal AI for spinning up sandboxes for code execution
Nebius, OpenAI, Anthropic and Hugging Face can be used for LLM calls
Nebius set by default for inference, with a priority on token speed that can be found on the platform
❤️ A very big thank you to the sponsors for the generous credits for this hackathon and Hugging Face and Gradio for putting this event together 🔥
Special thanks to Yuvi for putting up with us in the Discord asking for credits 😂
🚀 Multi-agent system for AI-powered search and code generation
What is the Shallow Research MCP Hub for Code Assistance?
Shallow Research Code Assistant is a sophisticated multi-agent research and code assistant built using Gradio's Model Context Protocol (MCP) server functionality. It orchestrates specialized AI agents to provide comprehensive research capabilities and generate executable Python code. This "shallow" research tool (Its definitely not deep research) augments the initial user query to broaden scope before performing web searches for grounding.
The coding agent then generates the code to answer the user question and checks for errors. To ensure the code is valid, the code is executed in a remote sandbox using the Modal infrustructure. These sandboxes are spawned when needed with a small footprint (only pandas, numpy, request and scikit-learn are installed).
However, if additional packages are required, this will be installed prior to execution (some delays expected here depending on the request).
Once executed the whole process is summarised and returned to the user.
📹 Demo Video
Click the badge above to watch the complete demonstration of the MCP Demo Shallow Research Code Assistant in action
Key information
I've found that whilst using VS Code for the MCP interaction, its useful to type the main agent function name to ensure the right tool is picked.
For example "agent research request: How do you write a python script to perform scaling of features in a dataframe"
This is the JSON script required to set up the MCP in VS Code
This is the JSON script required to set up the MCP Via Cline in VS Code
✨ Key Features
🧠 Multi-Agent Architecture: Specialized agents working in orchestrated workflows
🔍 Intelligent Research: Web search with automatic summarization and citation formatting
💻 Code Generation: Context-aware Python code creation with secure execution
🔗 MCP Server: Built-in MCP server for seamless agent communication
🎯 Multiple LLM Support: Compatible with Nebius, OpenAI, Anthropic, and HuggingFace (Currently set to Nebius Inference)
🛡️ Secure Execution: Modal sandbox environment for safe code execution
📊 Performance Monitoring: Advanced metrics collection and health monitoring
🏛️ MCP Workflow Architecture
The diagram above illustrates the complete Multi-Agent workflow architecture, showing how different agents communicate through the MCP (Model Context Protocol) server to deliver comprehensive research and code generation capabilities.
🚀 Quick Start
Configure your environment by setting up API keys in the Settings tab
Choose your LLM provider Nebius Set By Default in the Space
Input your research query in the Orchestrator Flow tab
Watch the magic happen as agents collaborate to research and generate code
🏗️ Architecture
Core Agents
Question Enhancer: Breaks down complex queries into focused sub-questions
Web Search Agent: Performs targeted searches using Tavily API
LLM Processor: Handles text processing, summarization, and analysis
Citation Formatter: Manages academic citation formatting (APA style)
Code Generator: Creates contextually-aware Python code
Code Runner: Executes code in secure Modal sandboxes
Orchestrator: Coordinates the complete workflow
Workflow Example
🛠️ Setup Requirements
Required API Keys
LLM Provider (choose one):
Nebius API (recommended)
OpenAI API
Anthropic API
HuggingFace Inference API
Tavily API (for web search)
Modal Account (for code execution)
Environment Configuration
Set these environment variables or configure in the app:
🎯 Use Cases
Code Generation
Prototype Development: Rapidly create functional code based on requirements
IDE Integration: Add this to your IDE for grounded LLM support
Learning & Education
Code Examples: Generate educational code samples with explanations
Concept Exploration: Research and understand complex programming concepts
Best Practices: Learn current industry standards and methodologies
🔧 Advanced Features
Performance Monitoring
Real-time metrics collection
Response time tracking
Success rate monitoring
Resource usage analytics
Intelligent Caching
Reduces redundant API calls
Improves response times
Configurable TTL settings
Fault Tolerance
Circuit breaker protection
Rate limiting management
Graceful error handling
Automatic retry mechanisms
Sandbox Pool Management
Pre-warmed execution environments
Optimized performance
Resource pooling
Automatic scaling
📱 Interface Tabs
Orchestrator Flow: Complete end-to-end workflow
Individual Agents: Access each agent separately for specific tasks
Advanced Features: System monitoring and performance analytics
🤝 MCP Integration
This application demonstrates advanced MCP (Model Context Protocol) implementation:
Server Architecture: Full MCP server with schema generation
Function Registry: Proper MCP function definitions with typing
Multi-Agent Communication: Structured data flow between agents
Error Handling: Robust error management across agent interactions
📊 Performance
Response Times: Optimized for sub-second agent responses
Scalability: Handles concurrent requests efficiently
Reliability: Built-in fault tolerance and monitoring
Resource Management: Intelligent caching and pooling
🔍 Technical Details
Python: 3.12+ required
Framework: Gradio with MCP server capabilities
Execution: Modal for secure sandboxed code execution
Search: Tavily API for real-time web research
Monitoring: Comprehensive performance and health tracking
Ready to experience the future of AI-assisted research and development?
Start by configuring your API keys and dive into the world of multi-agent AI collaboration! 🚀
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Tools
- ShallowCodeResearch_agent_citation_formatter
- ShallowCodeResearch_agent_code_generator
- ShallowCodeResearch_agent_llm_processor
- ShallowCodeResearch_agent_question_enhancer
- ShallowCodeResearch_agent_research_request
- ShallowCodeResearch_agent_web_search
- ShallowCodeResearch_code_runner_wrapper
- ShallowCodeResearch_get_cache_status
A sophisticated research assistant that orchestrates a 5-step workflow of connected AI agents to provide deep research capabilities including question enhancement, web search, summarization, citation formatting, and result combination.
- Technologies Used
- 🚀 Multi-agent system for AI-powered search and code generation
- What is the Shallow Research MCP Hub for Code Assistance?
- 📹 Demo Video
- Key information
- ✨ Key Features
- 🏛️ MCP Workflow Architecture
- 🚀 Quick Start
- 🏗️ Architecture
- 🛠️ Setup Requirements
- 🎯 Use Cases
- 🔧 Advanced Features
- 📱 Interface Tabs
- 🤝 MCP Integration
- 📊 Performance
- 🔍 Technical Details
Related MCP Servers
- -securityAlicense-qualityEnables iterative deep research by integrating AI agents with search engines, web scraping, and large language models for efficient data gathering and comprehensive reporting.Last updated -4275MIT License
- -securityAlicense-qualityAn agent-based tool that provides web search and advanced research capabilities including document analysis, image description, and YouTube transcript retrieval.Last updated -12Apache 2.0
- AsecurityFlicenseAqualityA powerful research assistant that conducts intelligent, iterative research through web searches, analysis, and comprehensive report generation on any topic.Last updated -422
- -securityAlicense-qualityProvides specialized AI-powered comprehensive research and analysis capabilities by integrating with advanced deep research agents, offering unlimited queries with no rate limits and faster performance than comparable services.Last updated -9857MIT License