Research Workflow
Open-source AI research assistant for VS Code + GitHub Copilot. Connects to PubMed, OpenAlex, Semantic Scholar, Europe PMC, CrossRef, and Zotero via MCP servers. Custom agents guide systematic reviews, academic writing, data analysis, and project man
What is Research Workflow?
Research Workflow is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open-source ai research assistant for vs code + github copilot. connects to pubmed, openalex, semantic scholar, europe pmc, crossref, and zotero via mcp servers. custom agents guide systematic reviews...
Open-source AI research assistant for VS Code + GitHub Copilot. Connects to PubMed, OpenAlex, Semantic Scholar, Europe PMC, CrossRef, and Zotero via MCP servers. Custom agents guide systematic reviews, academic writing, data analysis, and project man
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Open-source AI research assistant for VS Code + GitHub Copil
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx research-workflow-assistantConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Research Workflow
Research Workflow Assistant is an open-source, multi-server MCP suite that connects VS Code and GitHub Copilot to the major academic literature databases—PubMed, OpenAlex, Semantic Scholar, Europe PMC, CrossRef, and Zotero—through eleven specialized MCP servers. It provides PRISMA-compliant systematic review guidance, meta-analysis support with R/Python, ICMJE-compliant academic writing, and full project management via eight specialist AI agents. Researchers conducting evidence synthesis, clinical studies, or literature reviews can automate the full workflow from protocol design through manuscript submission within a single VS Code environment.
Prerequisites
- VS Code 1.99 or higher with GitHub Copilot extension and agent mode enabled
- Python 3.11 or higher installed
- NCBI API key (free, from NCBI account settings) for PubMed access
- Zotero API key and user ID (if using Zotero citation management)
- Optional: R 4.0+ and Quarto for reproducible data analysis outputs
Clone the repository
Clone the research-workflow-assistant repository and open it in VS Code.
git clone https://github.com/andre-inter-collab-llc/research-workflow-assistant.git
cd research-workflow-assistant
code .Create a Python virtual environment
Create and activate a Python virtual environment to isolate dependencies.
python -m venv .venv
source .venv/bin/activate # macOS/Linux
# .venv\Scripts\Activate.ps1 # Windows PowerShellInstall all MCP servers
Install all eleven MCP server packages and the main package with dev extras in one command.
pip install -e mcp-servers/_shared \
-e mcp-servers/pubmed-server \
-e mcp-servers/openalex-server \
-e mcp-servers/semantic-scholar-server \
-e mcp-servers/europe-pmc-server \
-e mcp-servers/crossref-server \
-e mcp-servers/zotero-server \
-e mcp-servers/zotero-local-server \
-e mcp-servers/prisma-tracker \
-e mcp-servers/project-tracker \
-e mcp-servers/chat-exporter \
-e mcp-servers/bibliography-manager
pip install -e ".[dev]"Configure environment variables
Copy the example .env file and fill in your API keys. NCBI_API_KEY is strongly recommended to avoid rate limiting on PubMed searches.
cp .env.example .env
# Edit .env and set:
# NCBI_API_KEY=your_ncbi_key
# OPENALEX_API_KEY=your_openalex_key
# ZOTERO_API_KEY=your_zotero_key
# ZOTERO_USER_ID=your_numeric_user_id
# PROJECTS_ROOT=./my_projectsValidate the setup
Run the validation script to confirm all MCP servers are installed and API connections are working correctly.
python scripts/validate_setup.pyEnable MCP servers in VS Code
Open VS Code, press Ctrl+Shift+P, and run 'MCP: List Servers' to confirm all servers appear. Then use GitHub Copilot Chat in agent mode to start research workflows.
Research Workflow Examples
Client configuration
The MCP servers are managed by VS Code's built-in MCP support. A representative config for Claude Desktop to use the PubMed server directly would look like this.
{
"mcpServers": {
"pubmed": {
"command": "python",
"args": ["-m", "pubmed_server"],
"cwd": "/path/to/research-workflow-assistant",
"env": {
"NCBI_API_KEY": "your_ncbi_api_key_here"
}
},
"openalex": {
"command": "python",
"args": ["-m", "openalex_server"],
"cwd": "/path/to/research-workflow-assistant",
"env": {
"OPENALEX_API_KEY": "your_openalex_key_here"
}
}
}
}Prompts to try
Use these agent-prefixed prompts in GitHub Copilot Chat to leverage the specialist agents.
- "@systematic-reviewer I want to conduct a systematic review on community health worker interventions for maternal mental health in LMICs"
- "@research-planner Help me design a research protocol for a randomized controlled trial on mindfulness-based stress reduction"
- "@data-analyst I have data extracted from 23 studies. Set up a random-effects meta-analysis using metafor in R"
- "@academic-writer Draft the Methods section for my systematic review following PRISMA guidelines"
- "@project-manager Initialize a new project called 'chronic-pain-review' in my_projects folder"Troubleshooting Research Workflow
PubMed searches return 429 rate limit errors
Set your NCBI_API_KEY in the .env file. Without a key, NCBI allows only 3 requests/second; with a key, the limit increases to 10/second. Get a free key at https://www.ncbi.nlm.nih.gov/account/.
MCP servers not appearing in VS Code after installation
Ensure VS Code 1.99+ is installed with GitHub Copilot extension and that agent mode is enabled in Copilot settings. Run 'python scripts/validate_setup.py' to verify server installations, then restart VS Code.
Zotero server fails to authenticate
Verify ZOTERO_API_KEY and ZOTERO_USER_ID are both set in .env. The user ID is a numeric value found on the Zotero API keys page (not your username). Generate a key at https://www.zotero.org/settings/keys.
Frequently Asked Questions about Research Workflow
What is Research Workflow?
Research Workflow is a Model Context Protocol (MCP) server that open-source ai research assistant for vs code + github copilot. connects to pubmed, openalex, semantic scholar, europe pmc, crossref, and zotero via mcp servers. custom agents guide systematic reviews, academic writing, data analysis, and project man It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Research Workflow?
Follow the installation instructions on the Research Workflow GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Research Workflow?
Research Workflow works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Research Workflow free to use?
Yes, Research Workflow is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Research Workflow Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Research Workflow? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Research Workflow in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Research Workflow?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.