"Deploying an MCP service in an offline environment" matching MCP servers:

Connects AI assistants to Swiss environmental data from BAFU, including air quality, hydrology, natural hazards, and open datasets, with no API keys required.

Provides access to Hong Kong government environment data, including the current Air Quality Health Index (AQHI) from monitoring stations across Hong Kong.

Provides access to UK Environment Agency's real-time flood monitoring data, enabling users to check flood warnings, monitor water levels and flow rates, and access historical measurements from monitoring stations across the UK.

Enables AI agents to retrieve free, source-linked decision methods and optional decision packs through MCP tools such as catalog, method, sample_pack, and pack_offer. It operates without model calls and disables payments by default.

Read-only MCP server for Energinet's public Energi Data Service. Enables dataset search, arbitrary dataset queries with filters, and CO2 emissions retrieval for DK1/DK2 without an API key.

Enables access to Australian real estate data through the Realty In Au API, supporting property listings, agent/agency information, property details, school lookups, and property search with various filters.

MCP server to access India Open Government Data (data.gov.in) resources via natural language queries.

Read-only MCP server for the July 2026 survey of AI in open-source design systems, enabling agents to query 19 systems' affordances, coercion techniques, and platform data via 9 tools, 2 resources, and 2 prompts.

Enables LLM clients to query an offline-first, read-only snapshot of a university Cluster of Excellence research-data platform — its projects, thematic sections, ~4,000 research items, people, institutions, collections, publications with searchable full text, podcasts and video transcripts. Every record carries a citable public URL, so findings can be traced back to the source.

Provides current weather conditions and forecasts for Singapore from official NEA APIs, enabling users to query real-time weather data and multi-day forecasts through natural language.

MCP server for creating and taking ENEM exams with official questions, including progress tracking, scoring, and interactive UI in MCP-compatible clients.

Enables searching FDA food recalls and adverse event reports through natural language, supporting filters and pagination.

Python based with all 29 tools that's available to developers from National Park Services (NPS)

An MCP server for querying the FDSN Web Service Event APIs of multiple seismological datacenters and retrieving earthquake information as JSON.

Per-unit cost of 13 back-office tasks done by a person vs by software, in the US, Greece and Ukraine, with an official statistic behind every hourly wage. Bundled data, works offline.

An MCP server that connects AI chatbots directly to data.gouv.fr, France’s national open data platform. It allows users to search, explore, and analyze thousands of public datasets simply by asking questions in natural language.

Checks whether a citation has been retracted, corrected, or flagged with an expression of concern by querying Crossref — including retractions that Crossref backfills from the Retraction Watch database, which publishers often never record in their own metadata. Lets an AI agent verify a DOI, or every DOI in a reference list, before using it in research or writing.

Enables MCP clients to retrieve live National Weather Service alerts for any US state and verify connectivity via an echo resource.

Enables querying Danish energy data—electricity prices, carbon intensity, consumption, production, grid capacity, balancing markets, and gas—from Energinet's public Energi Data Service without an API key.

An MCP server that lets AI agents search, save, preview, download, and cart satellite scenes from ISRO's Bhoonidhi portal in natural language, with search and saved queries requiring no login and downloads/cart operations using an out-of-band session.

An MCP server that enables AI to correctly search and query Tokyo's open data by automatically handling synonym variations, warning about misleading update timestamps, and skipping empty rows in API responses.

Enables querying domain trust scores, ratings, and reviews, searching domains, and posting reviews via natural language through the truster.info service.

An MCP server for SEC EDGAR written in Rust: company filings, full-text search, XBRL financials, insider transactions and company info. A single native binary; no API key.

DeepPVMapper is an open source, crowdsourced verified AI map of rooftop solar systems. The MCP serves as a endpoint to allow queries to the database (1.1M+ systems) in natural language. This work is based on my former PhD work.

An MCP server for exploring British and Irish hills (Munros, Wainwrights, Corbetts, Marilyns) with offline search, nearby hills, and detailed hill data, no API key required.

An MCP server for chemistry: it computes molecular weights and isotope distributions from chemical formulae and resolves compound name/formula lookups, backed by NIST atomic-weight data and a cached finder over multiple online and offline sources.

Enables offline, millisecond querying of a locally built SQLite snapshot of TibiaWiki, letting an agent resolve approximate page names, filter creatures and items by stats and damage modifiers, and find how any item is obtained via drops, vendors, or quest rewards. Every response reports when the index was generated, and no network calls are made.

An MCP server that puts open data on tap, enabling LLM clients to search, inspect, and query 30,000+ civic datasets from Socrata portals with built-in guardrails like row caps and actionable error messages.

Provides an MCP interface for accessing YOKATLAS (Turkish Higher Education Council Atlas) data, enabling LLM applications like Claude to search and retrieve details about undergraduate and associate degree programs in Turkey.

An MCP server providing tools to read articles, RSS feeds, NASA APOD, daily art, arXiv papers, poems, and historical events with a focus on clean, offline-friendly content.