StackData is an MCP server with 4 tools an agent can call, among them get_table, resolve_data, search_datasets. It answers at https://api.stackdata.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Official statistics, China censuses & yearbooks, and as-of customs tariffs with legal citations.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_table | Fetch a STORED table whole, by dataset id (families cn-nbs-census and cn-nbs-yearbook): labelled rows × columns with original-language labels, English overlay, units, and provenance down to the source file. Ids look like 'cn-nbs-census:2010 Inputs: dataset_id |
resolve_data | Ask a data question in English ('unemployment rate in Japan', 'compare GDP in Japan and Germany') — resolves to the best covering dataset and returns the observations, with coverage honesty (missing countries are reported, never papered ove Inputs: q, start, end |
search_datasets | Search StackData's catalog of 50k+ official statistical datasets (SDMX/World Bank dataflows, China censuses and yearbooks, tariff schedules). Multilingual: an English query finds Chinese-titled tables. Returns dataset ids usable with the ot Inputs: q, limit |
tariff_lookup | As-of customs-tariff lookup: which measures/duty rates apply to a goods code in a jurisdiction (eu, us, uk, jp), optionally from an origin, on a date. Duty expressions are verbatim; every measure carries its legal citation. Not legal advice Inputs: code, jurisdiction, origin, date, direction |
Every block below points at https://api.stackdata.io/mcp. Pick your client and copy.
claude mcp add --transport http stackdata https://api.stackdata.io/mcp
{
"mcpServers": {
"stackdata": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.stackdata.io/mcp"]
}
}
}{
"mcpServers": {
"stackdata": {
"url": "https://api.stackdata.io/mcp"
}
}
}{
"servers": {
"stackdata": {
"type": "http",
"url": "https://api.stackdata.io/mcp"
}
}
}{
"context_servers": {
"stackdata": {
"url": "https://api.stackdata.io/mcp"
}
}
}{
"mcpServers": {
"stackdata": {
"serverUrl": "https://api.stackdata.io/mcp"
}
}
}{
"mcpServers": {
"stackdata": {
"url": "https://api.stackdata.io/mcp"
}
}
}name: StackData
version: 0.0.1
schema: v1
mcpServers:
- name: StackData
type: streamable-http
url: https://api.stackdata.io/mcp{
"mcpServers": {
"stackdata": {
"httpUrl": "https://api.stackdata.io/mcp"
}
}
}{
"mcpServers": {
"stackdata": {
"type": "http",
"url": "https://api.stackdata.io/mcp"
}
}
}{
"mcpServers": {
"stackdata": {
"url": "https://api.stackdata.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.stackdata.io%2Fmcp&type=streamable_http&id=stackdata&name=StackData
It answered our last check on 24 October 2026 in 536 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by stackdata.io and served from api.stackdata.io, the vendor's own domain: https://api.stackdata.io/mcp.
4, as returned by the server's own tools/list on 22 September 2026: get_table, resolve_data, search_datasets, tariff_lookup.
It answered our last check on 24 October 2026 in 536 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.stackdata.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.stackdata. Endpoint host: api.stackdata.io. ARD identifier: urn:air:io.stackdata:mcp:stackdata.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.