io.github.Autario/autario-mcp
v3.0.1Connect your ads, shop, analytics, social, CRM and finance tools, and let AI explain the numbers.
Endpoint health
online- Last checked
- 11/20/2026, 7:16:33 AM
- Latency
- 158 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:io.github.Autario%2Fautario-mcp
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"io.github.Autario/autario-mcp": {
"url": "https://autario.com/mcp"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
16 shown · authentication unknown
analyze
Statistics computed server-side on verified autario indicators (World Bank, FRED, Eurostat, OECD, IMF, WHO, SEC): correlation, regression, growth, drivers, seasonality, value checks.
Schema valid · SHA-256 d445d5eaa023…
View input schema
{ "type": "object", "properties": { "action": { "type": "string", "enum": [ "describe", "correlate", "regression", "pct_change", "rolling_stats", "calculate", "lag_analysis", "seasonality", "find_drivers", "decompose_drivers", "what_matters", "verify_value" ], "description": "Which operation to run. describe = summary statistics and trend of one series, needs indicator, entity; correlate = correlation between two series, needs entity, a, b; regression = linear regression of y on x, needs entity, y, x; pct_change = percent change and growth over a period, needs entity, indicator; rolling_stats = rolling mean, sum or other window statistic, needs entity, indicator; calculate = arithmetic between two series, checked for compatible meaning, needs a, b, entity; lag_analysis = lead and lag between two series, needs a, b, entity; seasonality = trend, seasonal and residual parts of a series, needs indicator, entity; find_drivers = which candidate indicators move with a target, needs entity, target_indicator, candidates; decompose_drivers = share of a target's change explained by each candidate, needs target_indicator, candidates; what_matters = ranked factors behind an outcome, needs entity, outcome; verify_value = check a quoted number against the source, needs indicator, entity, time." }, "indicator": { "type": "string", "description": "describe, pct_change, rolling_stats, seasonality: Indicator id of a numeric series, exactly as find_data action \"indicators\" or get_data action \"profile\" return it (a public indicator or one of your own uploads or connector tables). verify_value: Indicator ID" }, "entity": { "type": "string", "description": "describe, regression, pct_change, rolling_stats, calculate, seasonality: Entity the series is read for: an ISO 3166 alpha-3 country code such as \"DEU\" or \"USA\", or an aggregate code such as \"WLD\" or \"EUU\" (the canonical name matches too). Use the codes find_data action \"indicators\" and get_data action \"profile\" accept. correlate, find_drivers: Entity code (e.g. DEU) lag_analysis: Entity code (e.g. USA) decompose_drivers: Entity code (e.g. DEU). Omit for entity-less private series. what_matters: Entity code (e.g. USA, DEU) verify_value: Entity code (e.g. DEU, USA, EUU)" }, "time": { "type": "string", "description": "describe, regression, pct_change, rolling_stats, calculate, lag_analysis, seasonality, find_drivers, decompose_drivers, what_matters: Optional time window. \"2010-2023\" keeps 2010 through 2023, \"2019-01-2024-06\" works by month, and a single \"2015\" keeps 2015 onward. Omitted or unparseable = the whole series. correlate: Optional time range: \"2010-2023\" verify_value: Time period (e.g. \"2023\" or \"2023-06\")" }, "a": { "type": "string", "description": "correlate: First indicator ID calculate: First operand A (the numerator of a ratio). Indicator id of a numeric series, exactly as find_data action \"indicators\" or get_data action \"profile\" return it (a public indicator or one of your own uploads or connector tables). lag_analysis: First indicator id (candidate leading series)" }, "b": { "type": "string", "description": "correlate: Second indicator ID calculate: Second operand B (the denominator of a ratio). Indicator id of a numeric series, exactly as find_data action \"indicators\" or get_data action \"profile\" return it (a public indicator or one of your own uploads or connector tables). lag_analysis: Second indicator id (candidate lagging series)" }, "full": { "type": "boolean", "description": "Return the full raw time series (heavy, many tokens). Default false → you get only the summary/stats, which is enough to ANSWER a question. Set true only when you must plot or export every point." }, "y": { "type": "string", "description": "Dependent variable (target) indicator ID" }, "x": { "type": "string", "description": "Independent variable (predictor) indicator ID" }, "period": { "type": [ "string", "number" ], "description": "pct_change: yoy | qoq | mom (default: yoy) seasonality: Seasonal period in time steps (12=monthly, 4=quarterly, 7=weekly). Auto-inferred from indicator frequency if omitted." }, "window": { "type": "number", "description": "Window size in periods (2-100, default 5)" }, "op": { "type": "string", "description": "rolling_stats: mean | std | min | max | sum (default: mean) calculate: ratio | ratio_pct | diff | sum | product (default: ratio)" }, "override": { "type": "boolean", "description": "Compute a combination autario refused as incompatible. Requires `reason`." }, "reason": { "type": "string", "description": "Why the refused combination is correct here. Returned with the result so a human can audit the decision." }, "max_lag": { "type": "number", "description": "lag_analysis: Max lag in periods (1-20, default 5) decompose_drivers: Max lead/lag periods to scan per candidate (0 disables, default 5, max 20)" }, "target_indicator": { "type": "string", "description": "The KPI you want to explain" }, "candidates": { "type": [ "array", "string" ], "items": { "type": "string" }, "description": "find_drivers: Candidate indicator IDs to test (max 30) decompose_drivers: Candidate indicator ids to decompose jointly (2-15) what_matters: Optional comma-separated candidate indicator ids. If omitted, auto-selects from ontology." }, "outcome": { "type": "string", "description": "Indicator id of the outcome metric" }, "expected": { "type": "number", "description": "The value you want to verify. Omit for existence-only check." } }, "required": [ "action" ], "additionalProperties": false }
Connections
streamable-http
https://autario.com/mcp