Agent Data Hub
Server Details
Official statistics and economic data for agents, with source and licence per answer. No key.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
ask_anything and find_data both accept a plain-language data question and return up to 10 labelled candidate series with call_api arguments, and both carry nearly identical 'when to use' guidance ('for a data question...'), so an agent has no reliable rule for picking one. get_history vs get_series is also a soft overlap (live-recorded change points vs archived series), though the descriptions do draw that line more clearly. The remaining tools (call_api, search_apis, report_issue) are distinct.
All names are snake_case and verb-first (find_data, get_history, get_series, call_api, search_apis, report_issue), giving a predictable pattern. ask_anything breaks the verb_noun shape with a vague 'anything' object, a minor deviation but the only one.
Seven tools is well-scoped for a data-hub: three discovery/query entry points, two retrieval paths and one feedback channel. Nothing feels padded, and no obvious capability is bundled into an overloaded mega-tool.
The surface covers discovery (search_apis, find_data, ask_anything), execution (call_api), history retrieval (get_series, get_history) and error feedback (report_issue) — a full lifecycle for the stated purpose. Gaps are minor: no bulk/multi-series fetch, no endpoint metadata or catalogue-listing beyond keyword search, and no pagination or filter detail for search results.
Available Tools
7 toolsask_anythingAnswer a data questionARead-onlyIdempotentInspect
Takes a plain-language data question (official statistics, central bank rates, FX, energy, weather, holidays, research metadata). Every answer has an outcome. "answer": the value, only when the asked measure is word for word one known name of a series and its place, level and time fit and no other series fits as well; it carries answered_with (compare it with your question before you use it); a value history holds only the newest values, full true returns all of it. "candidates": otherwise, like find_data, up to 10 labelled series (publisher title, place with code and level, unit, latest value, range, source, licence) with the call_api arguments of each: choose the one whose measure, place and time match the question and pass its arguments to call_api (that second call returns the value); if none matches, tell the user this service does not have it. "none": nothing fits, with a reason. mode "candidates" always lists, mode "strict" gives the answer or none, never candidates. Examples: "population of pakistan", "unemployment rate california 2024". When to use: for any data question when you do not know the endpoint id. For a task with several figures or countries pass questions, not one call each. Use call_api instead when you already have an id, get_series for a long numeric history. Read-only, no API key or signup. Free quota: 1000 calls/day per IP, shared across tools.
Inputs: full, mode, query, questions.
call_apiCall an endpointARead-onlyIdempotentInspect
Runs one endpoint by id with parameters and returns its data as compact JSON (source, license, data_freshness included). Bundles answer whole tasks in one call: bundle-location-brief (weather, time, holidays for a place), bundle-country-brief, bundle-eurozone-brief, bundle-energy-brief-de, bundle-npm-package-brief. When to use: you know the endpoint id (from search_apis, from alternatives or catalog_choices of ask_anything, or from the docs) and want to set parameters exactly, e.g. another country or date. params are the endpoint's own query parameters as listed by search_apis (example_query). Unknown ids or bad params return an error message naming the problem. Read-only, no API key or signup. Free quota: 1000 calls/day per IP, shared across tools.
Inputs: apiId (required), full, fields, params, +1 more.
find_dataFind candidate data seriesARead-onlyIdempotentInspect
Returns up to 10 data series that might answer a data question, each labelled with the publisher's title, place (code and level), unit, frequency, latest value, range, source and licence, and the call_api arguments that return exactly that series. Never returns a value on its own guess: status is "candidates" or "none" (with a reason). A candidate with related_only ("needs_place": no place named; "no_place": the series has no place, the question names one; "other_measure": it measures something else than asked) has no call_api arguments: it is related, not the asked series. A none with reason "needs_place" may carry calls: call_api arguments of the asked measure with {place} left open, to fill in with the place the user means. When to use: for a data question, pass query or the parts measure, place and period; then choose a candidate whose measure, place and time match the question and pass its call_api arguments to call_api. If none matches, tell the user this service does not have it. Read-only, no API key or signup. Free quota: 1000 calls/day per IP, shared across tools.
Inputs: limit, place, query, period, +1 more.
get_historyGet recorded endpoint historyARead-onlyIdempotentInspect
Returns change points this service recorded over time for an endpoint (e.g. exchange rates, weather) as compact CSV. Use the same params as the live call. When to use: to see how a live value (e.g. an exchange rate or the weather at a place) changed since this service started recording it. For long official histories use get_series instead. Returns an error if nothing was recorded for these params. Read-only, no API key or signup. Free quota: 1000 calls/day per IP, shared across tools.
Inputs: apiId (required), from, limit, fields, +1 more.
get_seriesGet a full time seriesRead-onlyIdempotentInspect
Returns complete numeric histories as compact CSV (t,value) from this service's archive of openly licensed series, e.g. ECB FX rates since 1999 (fx.EUR.USD), World Bank indicators for all countries since 1960 (wb.FP.CPI.TOTL.ZG.DE), ECB rates and 10y yields (ecb.rate.deposit, ecb.yield10y.IT), Eurostat, Statistics Canada, ONS and FAO series, German power prices (smard.price.day), sunspots since 1749 (noaa.sunspot-number). Pass q to search series ids, or id to fetch one: the answer starts with the latest value, the previous one and the place; without from/to/resample/limit it holds the newest 60 points (limit up to 5,000). When to use: for many periods of one number (e.g. yearly inflation since 2000, monthly FX since 2010), with from/to and resample. For the latest value with context use ask_anything; get_history only holds values this service recorded from live endpoints. Read-only, no API key or signup. Free quota: 1000 calls/day per IP, shared across tools.
Inputs: q, id, to, agg, +3 more.
report_issueReport a wrong valueAInspect
Reports a suspected error in data this service returned, for one series or one endpoint, to the operator: a kind from a fixed list and an optional short text (at most 500 characters), e.g. country, period and the value the publisher shows. Side effects: only stores the report for a manual check against the source; it changes no data, returns no data, and nobody replies. Text that looks like an email address, phone or account number is refused and not stored. When to use: only when a value from this service disagrees with its source or is clearly broken, not for questions or data requests. No API key; at most 10 reports a day per client, not counted against the data quota.
Inputs: kind (required), text, apiId, params, +1 more.
search_apisSearch the endpoint catalogARead-onlyIdempotentInspect
Searches the catalog of verified endpoints (official statistics, interest rates, FX, energy, weather, geo, holidays, research, developer tools) by keyword and returns the best matches (10 by default) with id, short description, parameter names and an example query. When to use: to browse what exists for a topic, or when ask_anything returned "unfulfilled" or a low-confidence match. Pass the chosen id to call_api. Does not fetch any data and does not count against the quota.
Inputs: limit, search, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
Statistics from 28 agencies: FRED, Eurostat, ECB, World Bank, OECD. Cited values, computed answers.
Official data with free samples, provenance, aggregations, freshness and agent-ready insights.
Official economic statistics for AI agents: GDP, inflation, trade and debt for 150+ countries.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to access official statistical and economic indicator datasets from Eurostat, World Bank, OECD, IMF, WHO, and national statistical offices across 150+ countries through natural-language dataset discovery, inspection, time-series retrieval, SQL queries, CSV export, and account/watchlist management.MIT
- AlicenseNot gradedqualityBmaintenanceReal prices people actually paid (homes, rents, fuel, energy, groceries, medicines) from official open data, with source, period, sample size and licence on every answer. Read-only, no API key.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to resolve places and statistical variables, then retrieve harmonised public statistics such as population, income, health, employment, and emissions with publisher provenance and child-place comparisons.90 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to query official open data for actual prices people paid across housing, rents, fuel, energy, groceries, medicines, medical care, airfares, contracts, farm goods, land and vehicles. Each answer includes a median or official figure, typical range, sample size, period, confidence, and source attribution.-
Glama MCP Gateway
Add one secure layer between your agents and this server.