{
  "markdown": "# mcp-un-sdg\n\nUN Sustainable Development Goals (SDG) Indicators MCP — UN Statistics Division.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | Description |\n|------|-------------|\n| `list_goals` | List the 17 UN Sustainable Development Goals (code, title, description). Optionally drill into one goal to get its targets and indicators. |\n| `list_indicators` | The queryable catalog of SDG indicators. Each indicator (e.g. \"1.1.1\") nests its data series with their series codes (e.g. \"SI_POV_DAY1\"). Use a series code as seriesCode in get_series_data. |\n| `list_series` | Flat list of all SDG data series (series code + description + goal/target/indicator it belongs to). Series codes are what you pass to get_series_data. Use this when you want the raw series list rather than the indicator-nested view from list_indicators. |\n| `list_geoareas` | List geographic areas with their M49 area codes (e.g. 1 = World, 4 = Afghanistan, 8 = Albania). Pass an M49 code as areaCode in get_series_data. |\n| `get_series_data` | Get observations for an SDG series in a geographic area over a time range. seriesCode comes from list_indicators/list_series; areaCode is an M49 code from list_geoareas. Returns { data: [...] } where each observation has value, timePeriodStart, geoAreaName, source, footnotes, etc. |\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"un-sdg\": {\n      \"url\": \"https://gateway.pipeworx.io/un-sdg/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/un-sdg/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Un Sdg data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 3403,
  "sha": "30740a37166b57607c42cb28b6108c410a9fe4729ae6f9f3ec47194f1d5e89de",
  "repo_slug": "pipeworx-io/mcp-un-sdg",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_un_sdg_d541be74/readme"
}