Query UN FAOSTAT food and agriculture statistics from a local SQLite mirror.
This MCP tool claims to expose UN FAOSTAT statistics via a local SQLite mirror, with typical MCP capabilities such as network access, code execution, and local data access, so the overall posture is mainly caution. Its presence in the official registry, open-source code, and recent maintenance lower supply-chain risk, though sparse documentation and multiple environment variables limit transparency.
The materials list several environment variables: FAOSTAT_DOMAINS, FAOSTAT_MIRROR_PATH, FAOSTAT_BULK_BASE_URL, CANVAS_PROVIDER_TYPE, and MCP_LOG_LEVEL. By name they look more like configuration values than classic high-sensitivity API secrets, but they may still reveal local paths, data-source configuration, or runtime mode and should be handled as configuration secrets.
It is known to connect to faostat.caseyjhand.com, and the description indicates access to FAOSTAT data via a local mirror, so network communication to a declared endpoint is expected. The materials do not specify what exact user inputs or telemetry may be sent, but there is no stated unrelated or unknown third-party endpoint.
The system checks explicitly mark this tool as executes-code, meaning it runs code/processes locally; this is a normal MCP capability. The available materials do not show requests for clearly excessive system privileges unrelated to statistical data access, nor any suspicious execution chain.
The description explicitly mentions a 'local SQLite mirror,' and the FAOSTAT_MIRROR_PATH variable indicates access to local mirror files/paths. Based on the materials, this access appears aligned with its stated function, but the missing README leaves the exact read/write scope, cache locations, and whether it modifies the local mirror unspecified.
The source is in the official registry, with a public source repository and updates within the past year, providing auditability and some maintenance signals; these are positive factors that reduce risk. The missing license, very low community stars, and absent README do limit transparency, but they are not by themselves enough to make it high risk.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.cyanheads/faostat-mcp-server" MCP server from askskill: Run: claude mcp add 'io-github-cyanheads-faostat-mcp-server' -- node @cyanheads/faostat-mcp-server
Search USDA food data and compare detailed nutrient information.
Search and query structured data from government open-data portals.
Query FEMA disaster declarations, aid programs, housing assistance, and flood insurance claims.
Browse, search, and query official Finnish statistical data through AI assistants.
Find air-quality stations and retrieve pollutant observations from government monitors.
Connect to and query multiple databases through one unified interface.