mcp-research-agent-system
A production-quality multi-agent research system with an arXiv MCP server and LangGraph-based research agents, providing search, details, and cached summaries via SQLite.
README
MCP Research Agent System
A production-quality multi-agent research system with an arXiv MCP server and LangGraph-based research agents.
Architecture
- MCP Server — Wraps the arXiv public API with SQLite caching (
search_papers,get_paper_details,get_cached_summary) - LangGraph Agents — Planner, Researcher, Synthesizer with validation & retry logic
- Structured Logging — Full state-machine trace as JSONL
Quick Start
# 1. Copy .env.example and fill in your LLM credentials
cp .env.example .env
# 2. Install dependencies
pip install -e ".[dev]"
# 3. Run the MCP server (stdio transport)
python scripts/run_mcp_server.py
# 4. In another terminal, run a research query
python scripts/run_agent.py --goal "Your research topic here"
Configuration
All settings via .env (see .env.example):
| Variable | Description | Default |
|---|---|---|
LLM_BASE_URL |
OpenAI-compatible API base URL | http://localhost:20128/v1 |
LLM_API_KEY |
API key | required |
LLM_MODEL |
Model name | gpt-4o-mini |
RESEARCH_AGENT_DB_PATH |
SQLite database path | data/research_agent.db |
LOG_DIR |
Trace log directory | logs/ |
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.