Skip to main content
Glama
Moreti2002

Polymath MCP

by Moreti2002

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
POLYMATH_EMAILNoA real contact e-mail. Unlocks the Unpaywall source (which requires it) and puts Crossref requests in its polite pool with better rate limits. Without it everything else still works.

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_papersA

Search academic papers across arXiv, OpenAlex, Crossref, DBLP, Europe PMC and Semantic Scholar. Results are deduplicated by DOI/arXiv id and sorted by citation count. Optionally restrict to specific sources or a year range.

get_paperA

Get details for one paper by DOI (e.g. '10.1145/3600006') or arXiv id (e.g. '2301.12345' or 'arXiv:2301.12345'). Merges metadata from every source that knows the paper, including an open-access PDF link when one exists.

search_codeA

Search code repositories on GitHub, e.g. to find the implementation of a paper or a library. Optionally filter by programming language.

search_hubA

Search the Hugging Face Hub for models or datasets. kind is either 'models' or 'datasets'. Results include linked arXiv ids when available, which connects a model or dataset back to its paper.

search_trendsA

Search practitioner discussions and trends on Hacker News, Stack Overflow and the Electronics Stack Exchange. Useful as a signal of real-world relevance and for practical questions about a technology.

search_componentsA

Search electronic component information from keyless sources: scanned datasheets and databooks on the Internet Archive and KiCad symbol libraries (which confirm a part's existence and canonical naming). No keyless commercial parts API exists, so coverage is partial; for practical component discussion also try search_trends, which covers the Electronics Stack Exchange.

search_standardsA

Search technical standards and specifications: IETF RFCs and Internet-Drafts (TCP, HTTP, DNS, TLS, QUIC, ...). The primary source for networking and internet systems specs.

list_sourcesA

List every available data source and the category it serves.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 8 tools

Disambiguation4/5

Most tools are clearly distinct by domain (papers, code, models, trends, components, standards). Minor ambiguity exists between search_components and search_trends, as both can surface component-related information, though one focuses on datasheets and the other on discussions.

Naming Consistency5/5

The majority of tools follow a consistent search_<domain> pattern (search_papers, search_code, search_hub, search_trends, search_components, search_standards). The remaining tools use clear verb_noun forms (get_paper, list_sources) that fit naturally without mixing conventions.

Tool Count5/5

With 8 tools, the server is well-scoped for its multi-domain research purpose. Each tool serves a distinct need in the discovery pipeline, and the count is neither too sparse nor overwhelming.

Completeness4/5

The toolset covers the core discovery lifecycle: searching papers, retrieving paper details, searching code, models/datasets, trends, components, and standards. Missing are detail-retrieval tools for non-paper entities (e.g., get_code, get_model), but search results appear to include sufficient information for most use cases.

Maintenance

ActivitySlowing
ResponsivenessNo issues