"Hugging Face" matching MCP servers:

Unified MCP server for discovering open datasets across Hugging Face, Zenodo, and Kaggle, with ranked search results and one-click Colab starter code generation.

Enables AI assistants to fetch sourced, citable face measurement percentiles, face type definitions and threshold rules, methodology and citation details, and to classify a face shape from four distances using the site's seven rules in order. Read-only and takes no photo.

Enables plain-English description of training data needs to search Hugging Face and GitHub, composing coverage-scored training packs without API keys or Bridge.

Enables querying and analyzing US federal grant single-audit filings, including audits, findings, and federal awards, using data from the Federal Audit Clearinghouse.

Runs a read-only MCP server over stdio with tools to search Hugging Face, Kaggle and data.gov at once, inspect a dataset's columns and types, licence terms, byte and row counts, files and last update, and compare licences across several datasets. It enables an assistant to check whether a dataset fits a task and is legally usable before recommending it, reading only public metadata rather than downloading whole datasets.

An MCP server exposing NACE Rev. 2.1 economic activity classification codes for AI agents, with tools to browse, search, and fuzzy-match codes.

Enables AI agents to look up any US House district or Senate race and get the incumbent, every FEC-registered candidate by party with receipts, disbursements and cash on hand, plus inferred primary winners and the primary, runoff and general election dates. A companion tool lists the races in a state so you can find the right district.

Enables verification of simple factual claims (e.g., capital cities) by checking against Wikidata, returning accuracy and confidence scores.