Starwell: World Data & Statistics

Official11 toolsLive

by Adarsh4052 · JavaScript

Statistics from 28 agencies: FRED, Eurostat, ECB, World Bank, OECD. Cited values, computed answers.

starwell-mcp (Model Context Protocol Server)

This MCP server provides statistics sourced from 28 agencies, including FRED, Eurostat, the ECB, and the World Bank, with cited values and computed answers. It is positioned as an interface for “verified data,” covering multiple official statistical and regulatory sources, based on its repository readme excerpt.

🛠️ Key Features

Statistics from 28 agencies (e.g., FRED, Eurostat, ECB, World Bank, OECD)
Cited values and computed answers
11 tools exposed by the server

🚀 Use Cases

Retrieving official statistical figures from participating agencies
Generating computed answers using cited source values

⚡ Developer Benefits

Standardized access to cross-agency statistics via MCP tools
Availability of cited values alongside computed outputs

⚠️ Limitations

The available documentation excerpt lists many source organizations, but does not define the full scope or exact tool capabilities beyond “11 tools.”

Captured live from the server via tools/list.

list_sources

List the official statistical sources served by this data layer (e.g. Statistics Canada, FRED), with dataset/series counts, cadence notes, and terms links. Start here to see what exists.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

search_catalog

Find series across ALL sources in one call: case-insensitive search over series ids, indicator names, geographies, and dataset titles (e.g. "unemployment canada", "10-year treasury", "CPI"). Returns candidate series with units, coverage, verification status, and license, plus datasetMatches from the wider dataset index — datasets whose series can be requested by source-native id and are fetched from the official source on first call. The fastest path from a question to the exact series id to fetch or pin in the answer tool.

Parameters3

query	string	required	Search terms, e.g. "unemployment rate canada"
source	string	optional	Optional source slug to restrict to, e.g. 'fred'
limit	integer	optional	Max results (default 20)

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "Search terms, e.g. \"unemployment rate canada\""
    },
    "source": {
      "type": "string",
      "description": "Optional source slug to restrict to, e.g. 'fred'"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Max results (default 20)"
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_datasets

List the datasets (official releases/tables) available in one source, with coverage dates and links to the official table pages.

Parameters1

source

string

required

Source slug, e.g. 'fred' or 'statcan'

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "Source slug, e.g. 'fred' or 'statcan'"
    }
  },
  "required": [
    "source"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_series

Full metadata for one series: indicator, unit, frequency, geography, coverage, its VERIFICATION STATUS (passing/stale/failing/unverified from golden-value + freshness checks against the live source), recent check records, and the citation to the official table.

Parameters2

source	string	required	Source slug, e.g. 'fred'
seriesId	string	required	Source-native series id, e.g. 'UNRATE' or 'v41690973'

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "Source slug, e.g. 'fred'"
    },
    "seriesId": {
      "type": "string",
      "description": "Source-native series id, e.g. 'UNRATE' or 'v41690973'"
    }
  },
  "required": [
    "source",
    "seriesId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_observations

Observation values for one series. Every value carries provenance (the exact source URL it came from, retrieval time, connector version) and the envelope carries the series verification status + citation. Defaults to the latest 60 points; use start/end (YYYY-MM-DD) or latest to control the window.

Parameters5

source	string	required
seriesId	string	required
start	string	optional	YYYY-MM-DD inclusive lower bound
end	string	optional	YYYY-MM-DD inclusive upper bound
latest	integer	optional	Return only the latest N points (default 60 when no start/end given)

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string"
    },
    "seriesId": {
      "type": "string"
    },
    "start": {
      "type": "string",
      "description": "YYYY-MM-DD inclusive lower bound"
    },
    "end": {
      "type": "string",
      "description": "YYYY-MM-DD inclusive upper bound"
    },
    "latest": {
      "type": "integer",
      "minimum": 1,
      "maximum": 2000,
      "description": "Return only the latest N points (default 60 when no start/end given)"
    }
  },
  "required": [
    "source",
    "seriesId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_series_stats

Latest value, previous, all-time min/max, mean, and change vs the previous period and vs a year ago — computed over the verified store, with the citation attached. The cheap way to answer "what is it now and how has it moved" without a full analysis run.

Parameters2

source	string	required	Source slug, e.g. 'fred'
seriesId	string	required	Series id, e.g. 'DGS10'

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "Source slug, e.g. 'fred'"
    },
    "seriesId": {
      "type": "string",
      "description": "Series id, e.g. 'DGS10'"
    }
  },
  "required": [
    "source",
    "seriesId"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

create_monitor

Create a monitor: when the store's refresh lands a new period or a revised value for the series, a series.updated webhook fires to your URL with the new value, verification status, and citation. Requires an API key (free with an account at /account); webhook must be https. Manage with list_monitors / delete_monitor.

Parameters3

source	string	required	Source slug, e.g. 'fred'
seriesId	string	required	Series id, e.g. 'DGS10'
webhookUrl	string	required	https URL to receive series.updated events

Raw schema

{
  "type": "object",
  "properties": {
    "source": {
      "type": "string",
      "description": "Source slug, e.g. 'fred'"
    },
    "seriesId": {
      "type": "string",
      "description": "Series id, e.g. 'DGS10'"
    },
    "webhookUrl": {
      "type": "string",
      "description": "https URL to receive series.updated events"
    }
  },
  "required": [
    "source",
    "seriesId",
    "webhookUrl"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

list_monitors

Monitors on your API key, with delivery health (last fired, failures, active).

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

delete_monitor

Parameters1

string

required

Monitor id from list_monitors

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Monitor id from list_monitors"
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

answer

The flagship: ask a natural-language question about the served official statistics. Returns a COMPUTED answer (real Python runs in a sandbox over the verified store — nothing is estimated by a model), the Plotly chart, the Python code, citations to the official tables, and a verification badge per series. Returns a refusal when no served series can answer. Takes 10-40 seconds. Requires a free API key (create at /account on the Starwell host; pass Authorization: Bearer dlk_... or set STARWELL_API_KEY on the starwell-mcp bridge) — keyless calls return key_required.

Parameters4

question	string	required
series	array	optional	Optional: pin exact series and skip AI resolution
start	string	optional	YYYY-MM-DD
end	string	optional	YYYY-MM-DD

Raw schema

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 3,
      "maxLength": 500
    },
    "series": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "source": {
            "type": "string"
          },
          "seriesId": {
            "type": "string"
          }
        },
        "required": [
          "source",
          "seriesId"
        ],
        "additionalProperties": false
      },
      "maxItems": 4,
      "description": "Optional: pin exact series and skip AI resolution"
    },
    "start": {
      "type": "string",
      "description": "YYYY-MM-DD"
    },
    "end": {
      "type": "string",
      "description": "YYYY-MM-DD"
    }
  },
  "required": [
    "question"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

deep_analysis

The moat: a PLANNED multi-section report on a question — the engine designs 3-4 orthogonal analyses (trend, statistics, outliers, cross-series relationships), runs real Python for each in the sandbox over the verified store, and synthesizes one decision-ready report. Every number computed, every series cited and verification-badged. Slower than answer (60-180 seconds) — use for "analyze", "break down", "give me a full picture" asks; use the answer tool for a single direct question. Requires a free API key (create at /account on the Starwell host; pass Authorization: Bearer dlk_... or set STARWELL_API_KEY on the starwell-mcp bridge) — keyless calls return key_required.

Parameters4

question	string	required
series	array	optional	Optional: pin exact series and skip AI resolution
start	string	optional	YYYY-MM-DD
end	string	optional	YYYY-MM-DD

Raw schema

{
  "type": "object",
  "properties": {
    "question": {
      "type": "string",
      "minLength": 3,
      "maxLength": 500
    },
    "series": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "source": {
            "type": "string"
          },
          "seriesId": {
            "type": "string"
          }
        },
        "required": [
          "source",
          "seriesId"
        ],
        "additionalProperties": false
      },
      "maxItems": 4,
      "description": "Optional: pin exact series and skip AI resolution"
    },
    "start": {
      "type": "string",
      "description": "YYYY-MM-DD"
    },
    "end": {
      "type": "string",
      "description": "YYYY-MM-DD"
    }
  },
  "required": [
    "question"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md4 KBView on GitHub

starwell-mcp

Starwell is the verified data layer for AI: official statistics from Statistics Canada, FRED, the U.S. Bureau of Labor Statistics, the World Bank, SEC EDGAR, the U.S. Treasury, the European Central Bank, the UK Office for National Statistics, INSEE (France), the Australian Bureau of Statistics, the OECD, Eurostat, INE (Spain), the Czech National Bank, ILOSTAT, Statistics Netherlands, the CDC, Statistics Sweden, Statistics Norway, Statistics Finland, Statistics Austria, the Department of Statistics Malaysia, the U.S. Bureau of Economic Analysis, the Central Statistics Office of Ireland, Statistics Denmark, Statistics Poland, Statistics Estonia, Statistics Iceland, and the U.S. Bureau of Transportation Statistics, served as MCP tools. Every observation carries provenance, every series carries a verification status backed by golden-value checks against the live source, and the answer tool returns computed results cited to the official table.

This package is a thin stdio bridge to the Starwell remote MCP server. The tool surface always matches the server, so new sources and tools appear without a package update.

Tools (12): search_catalog, list_sources, list_datasets, get_series, get_series_stats, get_observations, factory_status, answer, deep_analysis, create_monitor, list_monitors, delete_monitor. Reads are open; answer, deep_analysis, and the monitor tools need a free API key (STARWELL_API_KEY).

Install per client

Remote-capable clients can skip this package and add the URL directly: https://starwell.dev/api/starwell/mcp (Streamable HTTP).

Claude Code

claude mcp add --transport http starwell https://starwell.dev/api/starwell/mcp
# or via stdio:
claude mcp add starwell -- npx -y starwell-mcp

Claude Desktop / claude.ai

Settings, Connectors, Add custom connector, URL https://starwell.dev/api/starwell/mcp. On plans without remote connectors, use the desktop config:

json

{
  "mcpServers": {
    "starwell": { "command": "npx", "args": ["-y", "starwell-mcp"] }
  }
}

Cursor

.cursor/mcp.json:

json

{
  "mcpServers": {
    "starwell": { "command": "npx", "args": ["-y", "starwell-mcp"] }
  }
}

OpenAI Codex CLI

~/.codex/config.toml:

toml

[mcp_servers.starwell]
command = "npx"
args = ["-y", "starwell-mcp"]

Gemini CLI

~/.gemini/settings.json:

json

{
  "mcpServers": {
    "starwell": { "httpUrl": "https://starwell.dev/api/starwell/mcp" }
  }
}

ChatGPT (developer mode)

Settings, Apps, enable developer mode, add connector with the remote URL above.

Configuration

STARWELL_MCP_URL: override the endpoint (staging, self-hosted).
STARWELL_API_KEY: Bearer key from https://starwell.dev/account (free). Data reads work without one; answer, deep_analysis, and monitors require it.

Data licensing

Only openly licensed official sources are served, each with its license and attribution in every response. The set covers U.S. federal statistical works (public domain), the Statistics Canada Open Licence, World Bank CC BY-4.0, and the respective open licences of the ECB, OECD, ONS, INSEE, and ABS. This product uses the FRED API but is not endorsed or certified by the Federal Reserve Bank of St. Louis.

Docs: https://starwell.dev/docs

This repository is the source of the starwell-mcp npm package. It is generated from Starwell's main repository, so pull requests here may be applied upstream by hand — but issues are read and very welcome.

Install

Tools (11)

list_sourcessearch_cataloglist_datasetsget_seriesget_observationsget_series_statscreate_monitorlist_monitors

Configuration

Environment variables

STARWELL_API_KEYsecret

Free Bearer key from https://starwell.dev/account. Data reads work without one; answer, deep_analysis, and monitors require it.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "world-data-statistics": {
      "command": "npx",
      "args": [
        "-y",
        "starwell-mcp@0.2.2"
      ],
      "env": {
        "STARWELL_API_KEY": "<YOUR_STARWELL_API_KEY>"
      }
    }
  }
}

starwell-mcp (Model Context Protocol Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

list_sources

search_catalog

list_datasets

get_series

get_observations

get_series_stats

create_monitor

list_monitors

delete_monitor

answer

deep_analysis

starwell-mcp

Install per client

Claude Code

Claude Desktop / claude.ai

Cursor

OpenAI Codex CLI

Gemini CLI

ChatGPT (developer mode)

Configuration

Data licensing

Install

Configuration

Related servers