OurAirports MCP Server

Source-reviewed, not functionally tested

These details were checked against primary sources. Skill Road has not performed a practical client functionality test. Features and setup reflect project documentation, not independently confirmed operation.

Use airport data as structured reference material

OurAirports MCP Server is a community project maintained by cyanheads, Casey Hand. It makes a bundled OurAirports dataset available to MCP-capable AI clients. This is independent intermediary software, not an authoritative aviation service or an official OurAirports server. Its value is structured research: developers, analysts and research teams can inspect codes, locations and related reference information without building a separate CSV import for every small question. The assistant gains a convenient way to explore records, not a guarantee that every answer is current or operationally suitable.

Verify identifiers and locations explicitly

An airport may have several identifier types. IATA and ICAO codes are not interchangeable, and one place name can refer to several facilities. Ask for the selected code, country and coordinates alongside the airport name. When joining records from two systems, use an explicit identifier convention rather than a loose name match. Similar wording is insufficient evidence that two rows describe the same airport. Missing identifiers should remain missing instead of being filled in by the assistant merely to make a merged table look complete.

The documented interface includes airport discovery, detailed records, coordinate-based queries and information about runways, navaids and countries. These capabilities can help prepare a map or investigate an existing dataset. A radius search still needs appropriate coordinates; it does not guarantee that an arbitrary place name has been understood or located correctly. Check whether a returned list was capped. The number of displayed rows is not necessarily the total number of matching airports, and a concise response may omit records relevant to a later comparison.

A bundled snapshot is not a live aviation feed

The project says reference lookups operate on data distributed with the package. That approach can support local searches without a runtime data API. It does not establish how recent an installed snapshot is. OurAirports updates its downloads regularly, but a previously installed package does not automatically contain those changes. Record both package version and data vintage when an analysis needs to be reproducible. Plan updates deliberately and assess whether they change identifiers, counts or other results used by downstream systems rather than assuming reference data never changes.

Choose the deployment with the full data flow in mind

The documentation describes stdio and remote HTTP operation. The reviewed package requires Node.js 24 or newer or Bun 1.4.0 or newer, with no API key for its bundled data. Installation and data refreshes still need network access. A community-hosted endpoint receives the search terms and coordinates you send. Even with a local lookup process, the AI client or optional telemetry can transmit information. Offline reference lookup therefore does not make the entire assistant workflow automatically confidential or independent of network services and their operators.

Licensing and non-operational use boundaries

Server code is Apache-2.0-licensed. OurAirports releases its data to the public domain without guaranteeing accuracy or fitness for a particular use. Do not rely on this integration for real flight operations, safety-critical navigation or decisions requiring authoritative current aviation information. It can be useful for development, data cleaning and non-operational research. Keep unavailable values visible as gaps and prevent a fluent assistant response from implying official approval. Original-source inspection and an appropriate domain review remain essential whenever a result is important enough to be reused or shared.

Source review and verification limits

This entry was reviewed against the linked primary sources on 2 October 2026. Features and setup instructions reflect the project's documentation rather than a complete functional test performed by Skill Road. Before production use, connect with non-sensitive example data, inspect the enabled tools, and compare responses with their original source. Changes to the service or your client may require a fresh review. The review date is not an uptime guarantee.

An MCP client. The reviewed package requires Node.js 24 or newer or Bun 1.4.0 or newer locally. No API key is needed for the bundled dataset; assess its freshness separately.

Configure a local stdio entry with command npx, args ["-y", "@cyanheads/ourairports-mcp-server@0.2.4"] and MCP_TRANSPORT_TYPE=stdio or connect https://ourairports.caseyjhand.com/mcp over HTTP. Optionally set OURAIRPORTS_DATA_DIR to a reviewed local snapshot. Do not use it as a flight-planning source.

npx -y @cyanheads/ourairports-mcp-server@0.2.4

The bundled data requires no API key or account. Self-hosted HTTP operation still needs appropriate access controls.

Read-only airport, runway, navaid and country lookups plus coordinate-radius searches. No documented booking, live-flight or control operations.

According to the project, lookups use bundled data rather than a runtime upstream API. Installation and updates need network access. The community endpoint receives coordinates and search terms; consider AI-client processing and telemetry separately.

Community data without an accuracy guarantee; unsuitable for real flight operations or safety-critical navigation. Check snapshot date, code type, units and result caps. Do not send sensitive coordinates to public hosts.