ResearchTwin
mcp-server-researchtwin
MCP server for ResearchTwin — inter-agentic research discovery across a federated network of researcher digital twins.
Exposes the ResearchTwin platform API as Model Context Protocol tools, enabling AI agents to discover researchers, explore publications, datasets, repositories, and compute S-Index impact metrics.
Tools
Tool | Description |
| List all researchers registered on the platform |
| Get a researcher's profile with S-Index score |
| Get comprehensive research context with all data source metrics |
| Get publications with citation counts |
| Get datasets with QIC (Quality × Impact × Collaboration) scores |
| Get code repositories with QIC scores |
| Search across all researchers for papers, datasets, or repos |
| Get geographic affiliations for all researchers |
Related MCP server: mcp-semanticscholar
Resources
URI | Description |
| Platform information and available tools |
Installation
pip install mcp-server-researchtwinOr install from source:
git clone https://github.com/martinfrasch/researchtwin.git
cd researchtwin/mcp-server
pip install -e .Usage
Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"researchtwin": {
"command": "mcp-server-researchtwin"
}
}
}Claude Code
Add to your Claude Code MCP settings:
{
"mcpServers": {
"researchtwin": {
"command": "mcp-server-researchtwin"
}
}
}Custom base URL
To point at a local or self-hosted ResearchTwin instance:
RESEARCHTWIN_URL=http://localhost:8000 mcp-server-researchtwinOr in Claude Desktop config:
{
"mcpServers": {
"researchtwin": {
"command": "mcp-server-researchtwin",
"env": {
"RESEARCHTWIN_URL": "http://localhost:8000"
}
}
}
}Example conversations
Once connected, you can ask your AI agent:
"Who are the researchers on ResearchTwin?"
"Show me Martin Frasch's publications and S-Index score"
"Find all datasets related to fetal monitoring"
"What repositories have the highest QIC scores?"
"Show me the geographic distribution of the research network"
Requirements
Python 3.10+
Network access to
researchtwin.net(or your configured instance)
License
MIT
Available Tools
8 toolsdiscoverA
Search across all researchers for papers, datasets, or repositories matching a keyword.
Args: query: Search keyword (e.g. 'fetal', 'machine learning', 'turbulence'). type: Optional filter — 'paper', 'dataset', or 'repo'. Leave empty to search all types.
Returns matching items across all registered researchers, sorted by relevance. This is the primary tool for cross-researcher discovery.
Inputs: query (required), type. Returns: result
get_contextA
Get comprehensive research context for a researcher including all data source metrics.
Args: slug: Researcher identifier (e.g. 'martin-frasch').
Returns S-Index, paper impact, source connection status (Semantic Scholar, Google Scholar, GitHub, Figshare), dataset QIC scores, and repo QIC scores. More detailed than get_profile — use this when you need the full picture.
Inputs: slug (required). Returns: result
get_datasetsA
Get a researcher's datasets with QIC (Quality x Impact x Collaboration) scores.
Args: slug: Researcher identifier.
Returns Figshare datasets with DOIs, download/view counts, and QIC scores computed using FAIR-based quality assessment.
Inputs: slug (required). Returns: result
get_network_mapA
Get geographic affiliations for all researchers in the network.
Returns researchers with their institutional affiliations and coordinates, sourced from ORCID and Semantic Scholar. Useful for understanding the geographic distribution of the research network.
Inputs: no named parameters. Returns: result
get_papersA
Get a researcher's publications with citation counts.
Args: slug: Researcher identifier.
Returns papers from Semantic Scholar and Google Scholar (merged, deduplicated) with titles, years, citation counts, and URLs.
Inputs: slug (required). Returns: result
get_profileA
Get a researcher's profile with S-Index score and summary metrics.
Args: slug: Researcher identifier (e.g. 'martin-frasch'). Use list_researchers to find valid slugs.
Returns structured profile with S-Index, h-index, paper count, citation count, and links to papers/datasets/repos endpoints.
Inputs: slug (required). Returns: result
get_reposA
Get a researcher's code repositories with QIC scores.
Args: slug: Researcher identifier.
Returns GitHub repositories with stars, forks, language, and QIC scores computed using FAIR-based quality assessment.
Inputs: slug (required). Returns: result
list_researchersA
List all researchers registered on the ResearchTwin platform.
Returns researcher slugs and display names. Use a slug with other tools to explore a specific researcher's profile, papers, datasets, and repositories.
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose with no ambiguity. The tools are well-separated by function: discovery across researchers, getting different types of researcher-specific content (context, datasets, papers, repos, profile), listing researchers, and network mapping. The descriptions explicitly differentiate similar tools like get_context vs get_profile.
All tools follow a consistent verb_noun pattern with clear, descriptive names. The naming convention is perfectly uniform: discover, get_context, get_datasets, get_network_map, get_papers, get_profile, get_repos, list_researchers. Every tool name immediately communicates its function.
With 8 tools, this is well-scoped for a research platform. Each tool earns its place by covering distinct aspects of researcher data exploration: discovery, listing, detailed profiling, and specific content types. The count is appropriate for the domain without being overwhelming or insufficient.
The tool surface provides complete coverage for exploring a research network. It includes discovery across researchers, listing all researchers, comprehensive profiling (both summary and detailed context), and access to all research outputs (papers, datasets, repositories). The network map adds valuable geographic context, creating a well-rounded set with no obvious gaps.
Maintenance
Related MCP Connectors
Find engineers and scientists from papers, open source and patents. Each result links its sources.
Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.
The open-source talent graph for humans and AI agents. Find developers.
Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables discovery and analysis of research ecosystems by extracting metadata from paper URLs, GitHub repositories, and research names. Automatically finds related papers, code repositories, models, datasets, and authors across platforms like arXiv, HuggingFace, and GitHub.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query the Semantic Scholar Academic Graph for scholarly paper data, supporting tools for search, retrieval, and analysis.73 npmMIT
- AlicenseNot gradedqualityFmaintenanceEnables AI agents to search academic papers, analyze citations and authors, track trending research, and find semantically related work using free scholarly sources.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to conduct academic research workflows such as paper discovery, literature mapping, citation chasing, author pivots, citation repair, and regulatory or species document retrieval.MIT