"Adding functionality to large language models" matching MCP servers:

MCP server for consulting vehicle data from DETRAN TO official source. Read-only, pay-per-use, works with any MCP-compatible client.

Enables querying of a locally pinned snapshot of the Education-to-Workforce Indicator Framework — 99 indicators and 11.8M observations — to browse questions, describe metrics, resolve places, and fetch or rank data across national, state, county, and district levels.

This project implements a Model Context Protocol (MCP) server providing Formula One racing data using the Python FastF1 library. Inspired by an existing TypeScript server, it offers similar F1 data functionalities natively in Python via FastF1.

Enables searching government awards through the Sell to State API by proxying JSON-RPC to the live HTTP MCP endpoint, requiring an API key.

Enables consultation of negative debt certificates (Certidão Negativa de Débitos) from the Palmas, TO city government through an official source.

Enables natural language queries to official dental council registration data in Tocantins, Brazil. Read-only, hosted, and works with any MCP client.

Enables searching and retrieving UK research grants, award values, institutions, and publications from the UKRI Gateway to Research API without authentication.

Enables spatial analysis of large remote GeoParquet files directly from object storage without downloading or importing data, using DuckDB's predicate and projection pushdown to answer queries efficiently.

Provides read-only access to live Bay Area transit data, including routes, stops, real-time departures, vehicle positions, and service alerts, for use by large language models.

Provides real-time stock market data and company search functionality for the Colombo Stock Exchange (CSE). It enables AI assistants to retrieve current prices, change percentages, and ticker information for Sri Lankan listed companies.

A bridge between large language models and Dutch parliamentary data, providing access to Dutch parliamentary documents, debates, and member information from the Tweede Kamer.

Enables direct interaction with FamilySearch.org's shared Family Tree and historical records, including reading and adding people, facts, relationships, sources, notes, memories, record search, and image downloads, without needing a browser.

Enables Polish public holiday lookups and business-day arithmetic (e.g., adding business days, counting business days) using the Nager.Date API, defaulting to Poland but supporting 110+ countries.

Enables AI assistants to search, query, and analyze CMS healthcare datasets from data.cms.gov, supporting features like dataset discovery, filtering, and CSV download for large-scale analysis.

MCP server for accessing Japanese government statistics portal 'e-Stat' API, enabling language models to search and retrieve statistical data.

Provides access to Wikidata for Large Language Models through the Model Context Protocol, offering tools for entity search, detailed retrieval, SPARQL queries, relation exploration, and property-based searches.

Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.

Enables search and retrieval of calibrated SWAT+ watershed models, national groundwater lithology and PFAS inventories, plus API-key-secured ordering and downloading of custom watershed models.

Enables federated search across 10 open-knowledge providers via Open Idea. Users can search for papers, code, datasets, models, hardware, and videos using natural language queries.

Enables read-only consultation of official vehicle damage notices of medium and large value from Minas Gerais, with results delivered to any MCP client on a prepaid, per-query basis.