StackData MCP

Provides Model Context Protocol tools to access over 59,000 public statistical datasets from global sources like NBS, Eurostat, and World Bank. Supports search, catalog export, tariff lookup, and resolving questions into structured tables with legal citations.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by StackData

MCP endpoint (Streamable HTTP)

https://api.stackdata.io/mcp

Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (6)

search_datasets
get_table
tariff_lookup
resolve_data
get_structure
get_series

6 of 6 have a description · 0 of 6 declare behavior hints · 4 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 7:40 PM UTC
Passed Official MCP Registry namespace is tied to stackdata.io · Nov 6, 2026, 6:33 PM UTC
Passed Endpoint is on the registry namespace domain · Nov 6, 2026, 6:33 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Search for statistical data in any language
Lookup customs tariffs with legal citations
Resolve natural language questions into data tables
Export full statistical catalogs

Source and maintenance

Vendor evidenceRegistry 0.1.0

mcp-registry: io.stackdata/stackdata@0.1.0 Project website

Protocol and capabilities

Server: stackdata 0.1
MCP protocol negotiated in check: 2025-06-18
Tools: 6 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

StackData: official statistics and customs tariffs for agents. Start with search_datasets or resolve_data; get_table serves whole stored tables; tariff_lookup answers as-of duty questions for eu/us/uk/jp. Anonymous use is quota-limited; pass an API key as the x-api-key header.

Tools

6 advertised

search_datasets

Advertised by the server during the last successful anonymous check.

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 other tools.

search_datasets input schema

{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "search query"
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    }
  }
}

get_table

Advertised by the server during the last successful anonymous check.

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_a0101a'.

get_table input schema

{
  "type": "object",
  "required": [
    "dataset_id"
  ],
  "properties": {
    "dataset_id": {
      "type": "string",
      "description": "catalog dataset id"
    }
  }
}

tariff_lookup

Advertised by the server during the last successful anonymous check.

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.

tariff_lookup input schema

{
  "type": "object",
  "required": [
    "code"
  ],
  "properties": {
    "code": {
      "type": "string",
      "description": "goods code, 2-10 digits (HS/TARIC/HTS)"
    },
    "date": {
      "type": "string",
      "description": "as-of date YYYY-MM-DD, default today"
    },
    "origin": {
      "type": "string",
      "description": "ISO2 origin country (eu/uk only)"
    },
    "direction": {
      "enum": [
        "import",
        "export"
      ],
      "type": "string",
      "default": "import"
    },
    "jurisdiction": {
      "enum": [
        "eu",
        "us",
        "uk",
        "jp"
      ],
      "type": "string",
      "default": "eu"
    }
  }
}

resolve_data

Advertised by the server during the last successful anonymous check.

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 over).

resolve_data input schema

{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "the question"
    },
    "end": {
      "type": "integer",
      "description": "end year"
    },
    "start": {
      "type": "integer",
      "description": "start year"
    }
  }
}

get_structure

Advertised by the server during the last successful anonymous check.

The published structure of one dataset, free: its dimensions with every member code and label, frequencies, period coverage, the ISO3 countries it serves, and whether it is servable. Call this before get_series to learn the codes to send. Dataset ids come from search_datasets.

get_structure input schema

{
  "type": "object",
  "required": [
    "dataset"
  ],
  "properties": {
    "dataset": {
      "type": "string",
      "description": "catalog dataset id, e.g. 'ilo-sdmx:DF_X'"
    }
  }
}

get_series

Advertised by the server during the last successful anonymous check.

Fetch ONE series with every dimension named by you (no guessing or relaxing): dataset, ISO3 countries, an ISO period range and a member code for every dimension from get_structure. Returns status ok/empty/refused with each value's provenance, and the missing country-periods listed. A bad request is a named 400 error saying which field and what is allowed.

get_series input schema

{
  "type": "object",
  "required": [
    "dataset",
    "countries",
    "period",
    "select"
  ],
  "properties": {
    "period": {
      "type": "object",
      "required": [
        "start",
        "end"
      ],
      "properties": {
        "end": {
          "type": "string",
          "pattern": "^\\d{4}(-Q[1-4]|-(0[1-9]|1[0-2]))?$",
          "description": "Last period, same form and frequency as start."
        },
        "start": {
          "type": "string",
          "pattern": "^\\d{4}(-Q[1-4]|-(0[1-9]|1[0-2]))?$",
          "description": "First period, ISO form: YYYY, YYYY-Qn or YYYY-MM. Must match a frequency the dataset serves."
        }
      },
      "description": "Inclusive ISO period range. \"latest\" is not accepted: name the periods you want. Annual 2020, quarterly 2020-Q1, monthly 2020-01.",
      "additionalProperties": false
    },
    "select": {
      "type": "object",
      "description": "A member code for every dimension of the dataset (other than geography and time) as listed in /structure, including frequency. Every dimension must be named; a missing or unknown dimension or code is a 400, never defaulted.",
      "additionalProperties": {
        "type": "string"
      }
    },
    "dataset": {
      "type": "string",
      "description": "A dataset id from the catalog, as returned by search (/v1/search, or the search_datasets MCP tool), e.g. \"ilo-sdmx:DF_X\"."
    },
    "countries": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 25,
      "minItems": 1,
      "description": "ISO 3166-1 alpha-3 codes (e.g. \"JPN\") or an aggregate code listed in the dataset's /structure. 1 to 25 entries."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

2026-11-07: 2 of 2 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 273 ms
95th percentile latency: 273 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 7:40 PM UTC · probe · passed · 273 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http stackdata-mcp https://api.stackdata.io/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add stackdata-mcp --url https://api.stackdata.io/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable stackdata-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "stackdata-mcp": {
      "url": "https://api.stackdata.io/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "stackdata-mcp": {
      "type": "streamableHttp",
      "url": "https://api.stackdata.io/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start stackdata-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "stackdata-mcp": {
      "type": "http",
      "url": "https://api.stackdata.io/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http stackdata-mcp https://api.stackdata.io/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://api.stackdata.io/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "stackdata-mcp": {
      "serverUrl": "https://api.stackdata.io/mcp"
    }
  }
}

Let your agent find its tools

Find servers like StackData MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

Do you run StackData MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing