ResearchMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersC | Search for academic papers on OpenAlex based on a query. Args: query: The research topic or keywords to search for max_results: Maximum number of papers to return (default: 5) year_from: Only include papers from this year onwards (optional) Returns: A formatted string with paper details including titles, authors, citations, and URLs |
| get_paper_abstractA | Get the full abstract for a specific paper. Args: paper_id: The OpenAlex paper ID (from search_papers results) Returns: The paper's abstract text with title and metadata |
| extract_claimsA | Extract key claims and findings from a paper's abstract. Args: paper_id: The OpenAlex paper ID Returns: Structured list of claims extracted from the paper |
| compare_papersC | Compare claims across multiple papers to find contradictions and consensus. Args: paper_ids: Comma-separated list of OpenAlex paper IDs (e.g., "W123,W456,W789") Returns: Abstracts from all papers for comparison analysis |
| get_citationsA | Get citation network for a paper - see what cites it and what it cites. Args: paper_id: The OpenAlex paper ID direction: "cited_by" (papers citing this), "references" (papers this cites), or "both" max_results: Maximum number of citations to return per direction (default: 10) Returns: Citation network information with paper details |
| find_research_gapsB | Analyze multiple papers on a topic to identify research gaps and unanswered questions. Args: query: Research topic to analyze num_papers: Number of papers to analyze (default: 5, max: 10) Returns: Analysis of research gaps, limitations, and future research directions |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: compare_papers analyzes multiple papers for contradictions, extract_claims processes individual paper content, find_research_gaps identifies gaps across papers, get_citations handles citation networks, get_paper_abstract retrieves single paper metadata, and search_papers finds papers by query. The descriptions clearly differentiate their functions, eliminating any ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case: compare_papers, extract_claims, find_research_gaps, get_citations, get_paper_abstract, and search_papers. The verbs (compare, extract, find, get, search) are appropriate and distinct, creating a predictable and readable naming convention throughout the set.
With 6 tools, this server is well-scoped for academic research assistance. Each tool earns its place by covering essential research workflows: searching papers, retrieving abstracts, extracting claims, comparing papers, analyzing gaps, and exploring citations. This count is neither too sparse nor bloated, fitting the domain perfectly.
The tool set covers core research workflows comprehensively, including search, retrieval, analysis, and comparison. Minor gaps exist, such as no tools for saving/bookmarking papers or tracking research progress, but agents can work around these. The surface supports end-to-end research tasks without dead ends.