Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Autario/autario-mcp

REMOTE · AUTARIO.COM · 2 COMPONENTS

Connect your ads, shop, analytics, social, CRM and finance tools, and let AI explain the numbers.

0 this week 66 Trust /100

Last scanned (23 hours ago)

Scores higher than 51% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Data and Analytics

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability70
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 12015 tokens (~750/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability check failed: schema churn in the 11 days we've observed: 79 tool removals, 0 breaking changes, 0 auth/transport breaks, 12 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 0
    • “markets” added an optional parameter “min_scored” cosmetic
    • “markets” added an optional parameter “party” cosmetic
    • “markets” added an optional parameter “metric” cosmetic
    • “markets” reworded the description of “action” cosmetic
    • “markets” reworded the description of “limit” cosmetic

    5 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 13 Nov 26 −2
    • Stability: 0.07 → fail ▼ security
    • A breaking change shipped without a version bump: still 3.0.1 ▼ security
    • Tool “calculate” was removed ▼ security
    • Tool “clear_rows” was removed ▼ security
    • Tool “compare_entities” was removed ▼ security
    • Tool “congress_trades” was removed ▼ security
    • Tool “connector_health” was removed ▼ security
    • Tool “content_360” was removed ▼ security
    • Tool “copy_experiments” was removed ▼ security
    • Tool “correlate” was removed ▼ security
    • Tool “create_app” was removed ▼ security
    • Tool “create_chart_from_spec” was removed ▼ security
    • Tool “create_dataset” was removed ▼ security
    • Tool “decompose_drivers” was removed ▼ security
    • Tool “delete_app” was removed ▼ security
    • Tool “delete_dataset” was removed ▼ security
    • Tool “describe” was removed ▼ security
    • Tool “discover_by_topic” was removed ▼ security
    • Tool “find_drivers” was removed ▼ security
    • Tool “geo_experiment” was removed ▼ security
    • Tool “get_app_artifact” was removed ▼ security
    • Tool “get_app_context” was removed ▼ security
    • Tool “get_app_preview_url” was removed ▼ security
    • Tool “get_chart” was removed ▼ security
    • Tool “get_company_fundamentals” was removed ▼ security
    • Tool “get_company_snapshot” was removed ▼ security
    • Tool “get_connector_status” was removed ▼ security
    • Tool “get_dataset_info” was removed ▼ security
    • Tool “get_dataset_schema” was removed ▼ security
    • Tool “get_engine_report” was removed ▼ security
    • Tool “get_entity_data” was removed ▼ security
    • Tool “get_entity_profile” was removed ▼ security
    • Tool “get_investor_portfolio” was removed ▼ security
    • Tool “get_politician_trades” was removed ▼ security
    • Tool “get_traction_overview” was removed ▼ security
    • Tool “lag_analysis” was removed ▼ security
    • Tool “list_apps” was removed ▼ security
    • Tool “list_chart_candidates” was removed ▼ security
    • Tool “list_charts” was removed ▼ security
    • Tool “list_connectors” was removed ▼ security
    • Tool “list_indicators” was removed ▼ security
    • Tool “list_investors” was removed ▼ security
    • Tool “list_overlays” was removed ▼ security
    • Tool “list_politicians” was removed ▼ security
    • Tool “list_proposals” was removed ▼ security
    • Tool “marketing_report” was removed ▼ security
    • Tool “outreach_prospects” was removed ▼ security
    • Tool “pct_change” was removed ▼ security
    • Tool “projects” was removed ▼ security
    • Tool “propose_column” was removed ▼ security
    • Tool “propose_corrections” was removed ▼ security
    • Tool “propose_flags” was removed ▼ security
    • Tool “propose_mappings” was removed ▼ security
    • Tool “publish_app” was removed ▼ security
    • Tool “publish_chart” was removed ▼ security
    • Tool “query_dataset” was removed ▼ security
    • Tool “regression” was removed ▼ security
    • Tool “reject_proposals” was removed ▼ security
    • Tool “remove_overlay” was removed ▼ security
    • Tool “request_chart” was removed ▼ security
    • Tool “rolling_stats” was removed ▼ security
    • Tool “screen_stocks” was removed ▼ security
    • Tool “search_datasets” was removed ▼ security
    • Tool “seasonality_decomposition” was removed ▼ security
    • Tool “seo_360” was removed ▼ security
    • Tool “social_360” was removed ▼ security
    • Tool “unpublish_app” was removed ▼ security
    • Tool “update_app_manifest” was removed ▼ security
    • Tool “update_chart” was removed ▼ security
    • Tool “update_developer_profile” was removed ▼ security
    • Tool “upload_app_bundle” was removed ▼ security
    • Tool “verify_value” was removed ▼ security
    • Tool “what_matters” was removed ▼ security
    • Tool “who_holds” was removed ▼ security
    • Tool “write_app_artifact” was removed ▼ security
    • Tool “write_rows” was removed ▼ security
    • Tool “get_my_workspace” was removed ▼ security
    • Tool “ai_visibility_prompts” was removed ▼ security
    • Tool “accept_proposals” was removed ▼ security
    • Tool “ai_visibility_360” was removed ▼ security
    • Tool “audience_360” was removed ▼ security
    • Tool “bubble_or_not” was removed ▼ security
    • New tool “app_settings”, which the server declares destructive security
    • New tool “apps”, which the server declares destructive security
    • New tool “charts”, which the server declares destructive security
    • New tool “delete”, which the server declares destructive security
    • Tool “chart_instructions” rewrote its description, which is the text the model reads security
    • Tool “refresh_connector” rewrote its description, which is the text the model reads security
    • Tool “report_data_issue” rewrote its description, which is the text the model reads security
    • Tool “social_publish” rewrote its description, which is the text the model reads security
    • Schema quality: 409 → 741 ▼ functional
    • New tool “analyze” functional
    • New tool “app_report” functional
    • New tool “find_data” functional
    • New tool “get_data” functional
    • New tool “markets” functional
    • New tool “my_workspace” functional
    • New tool “proposals” functional
    • New tool “write_data” functional
    • “refresh_connector” reworded the description of “connector_id” cosmetic
    • “report_data_issue” reworded the description of “dataset_id” cosmetic
  • 12 Nov 26 +1
    • New tool “update_developer_profile” functional
  • 11 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 3.0.0 → 3.0.1 functional
  • 10 Nov 26 67

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://autario.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=autario.com CN=WE1,O=Google Trust Services,C=US 26 Sept 2026 25 Dec 2026 ECDSA 256 ECDSA-SHA256 4a582257fbf3bfb51329f052dd09b47f
SANs: autario.com, *.autario.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of autario.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
autario.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://autario.com/mcp Verified 200
http (plaintext) http://autario.com/mcp HTTPS enforced 301 https://autario.com/mcp
MCP tools · 16 exposed · ~12,015 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
analyze ~1,167

Statistics computed server-side on verified autario indicators (World Bank, FRED, Eurostat, OECD, IMF, WHO, SEC): correlation, regression, growth, drivers, seasonality, value checks.

NameTypeReqDescription
astring–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…
actionstringyesWhich 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…
bstring–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…
candidatesarray|string–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 omitte…
entitystring–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…
expectednumber–The value you want to verify. Omit for existence-only check.
fullboolean–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.
indicatorstring–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…
max_lagnumber–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)
opstring–rolling_stats: mean | std | min | max | sum (default: mean) calculate: ratio | ratio_pct | diff | sum | product (default: ratio)
outcomestring–Indicator id of the outcome metric
overrideboolean–Compute a combination autario refused as incompatible. Requires `reason`.
periodstring|number–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.
reasonstring–Why the refused combination is correct here. Returned with the result so a human can audit the decision.
target_indicatorstring–The KPI you want to explain
timestring–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-…
windownumber–Window size in periods (2-100, default 5)
xstring–Independent variable (predictor) indicator ID
ystring–Dependent variable (target) indicator ID

No output schema declared.

No examples provided.

app_report ~1,999

The computed report of an autario data app on the caller's own connected data (Google Search Console, GA4, Instagram, Facebook, TikTok, YouTube, LinkedIn, Meta Ads, Google Ads, Shopify, ChatGPT and other assistants), or a public bubble check on a stock.

NameTypeReqDescription
appstringyesWhich operation to run. audience_360 = audience, acquisition and conversion across web and social (sign-in); seo_360 = Search Console actions: gaps, decay, cannibalization (sign-in); content_360 = wh…
brandstring–audience_360: The brand (connector grouping) id to report on, as a uuid. Omitted means the brand selected in the autario app (the account's stored brand choice), so you see what the user sees on scre…
brand_termstring–Optional brand TERM override for the brand-vs-generic query split (default: derived from the GSC property). Renamed from `brand` on 2026-09-22, when that word became the connector grouping everywhere…
channelstring–Optional single-channel filter (sections that cannot honor it say so in notes).
chart_typestring–Optional render style for the fundamental: line or bar. Default is the app's smart choice (bars for quarterly reports, line for daily-derived metrics).
clientstring–Deprecated spelling of `brand`, still accepted so callers written before 2026-09-22 keep working. Pass `brand`.
countriesstring–Optional comma-separated ISO country codes filter, e.g. "DEU,USA".
daysinteger–seo_360: Analysis window in days (7-90, default 28), anchored at the newest day of the caller's data. The trend comparison uses the same-length window before it. content_360: Analysis window in days…
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…
fromstring–audience_360: Custom window start (YYYY-MM-DD), only with range=custom. marketing_report: Start day (YYYY-MM-DD) when period is "custom". An unusable pair falls back to the default window rather than…
groupstring–For "list": which axis the cards are folded on. Default "okr", which is the axis that answers "does everything we do pay into something we agreed".
idstring–The id of the thing to read or change: the project for "get" and "update", the objective for "update_objective", the key result for "update_key_result".
instancesstring–Optional comma-separated connector instance ids, to narrow the report to some of the connections inside the selected brand (for example one of two Search Console properties). Omitted means all of the…
metricstring–Optional fundamental to overlay against price. One of the labels from the company's available metrics (e.g. "Revenue", "Net Income", "Diluted EPS", "Market Cap", "P/E Ratio", "Earnings Yield", "Share…
periodstring–The reporting window. Default last-30. "this-week" runs Monday to today and compares to the same weekdays one week earlier; "custom" needs `from` and `to`.
rangestring–audience_360: Time window preset. Relative presets anchor at the newest data day. Default 90d. Use "custom" together with from/to. bubble_or_not: Optional time window for the chart. Default ALL (full…
scalestring–Optional value scale. "absolute" = raw values on a dual axis. "indexed" = both series rebased to 100 at the window start = relative performance on one shared %-axis (best for "did the price outrun th…
sectionsarray–audience_360: Which report sections to return. Default ["overview","channels"]. Request only what the question needs (token efficiency); call again for more. seo_360: Which report sections to return.…
sortstring–social_360: How the cross-platform top-post list is ranked (posts section). Default engagement. The three rates rank only posts whose platform reports them (Instagram today). projects: For "list": th…
tickerstring–US stock ticker symbol, e.g. AAPL, MSFT, NVDA, TSLA, AMZN
tostring–audience_360: Custom window end (YYYY-MM-DD), only with range=custom. marketing_report: End day (YYYY-MM-DD) when period is "custom".

No output schema declared.

No examples provided.

app_settings ~1,809

Change settings of the caller's autario apps: AI Visibility prompts and assistants (ChatGPT, Claude, Gemini, Perplexity), project board items, and the public developer profile.

NameTypeReqDescription
actionstringyesWhich operation to run. prompts_list = AI Visibility prompts and assistant selection of a brand, needs brand; prompts_add = store new AI Visibility prompts, needs brand; prompts_remove = set AI Visib…
aggregationstring–For key results: how its countries add up to a region. sum (default) for counts and money, average for rates and levels, none lists the countries without a total.
assistantsarray–For "set_assistants": the full list of assistants this brand runs from now on (replaces the current selection). An empty array returns to the app default.
baselinenumber–For key results: where the number started. Attainment runs from baseline to target.
biostring–Up to 280 characters about you or what you build.
brandstring–Brand name or brand id (required). With several brands on the account the name must match one of them exactly (case-insensitive); the tool answers with the list when it does not.
briefstring–A short description of what the project is.
budget_amountnumber–Budget. Needs budget_currency. Never converted between currencies.
budget_currencystring–Three letter currency code of the budget, e.g. EUR.
commitmentstring–For objectives: committed (expected at 1.0) or aspirational (0.7 is a good outcome). Changes the status rule of its key results, never a number.
contributorsarray–Everyone else working on it. These names are what the person axis groups by, together with the owner.
countrystring–The region or country that runs it, in the account's own words ("DACH", "Nordics"), not an ISO code.
country_columnstring–For key results with dataset_id: the column that names the country of a row (autario_entity when the dataset has it). value_column is then read per country; a country the dataset lacks keeps its type…
country_valuesarray–For key results: the value per country, [{ country, current, target }]; country as a name or ISO code. A region total uses these; several countries without values are never split.
dataset_idstring–For key results: the dataset the value is read from (any dataset on this account).
directionstring–For key results: whether higher or lower is better. Default increase.
display_namestring–Name shown on the page, up to 60 characters. Defaults to the handle.
effort_daysnumber–Estimated effort in person days.
ends_onstring–For objectives: end of that window, YYYY-MM-DD.
filter_columnstring–For key results: optional column to filter the dataset on.
filter_valuestring–For key results: the value filter_column must have.
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…
functionstring–The function that contributes it ("Marketing", "Supply chain").
github_urlstring–Your GitHub profile, on github.com.
groupstring–For "list": which axis the cards are folded on. Default "okr", which is the axis that answers "does everything we do pay into something we agreed".
guardrail_notestring–For key results: how this number could be reached the wrong way.
guards_idstring–For key results: makes this key result a GUARDRAIL of that key result.
handlestring–Your public handle, set once (lowercase, 3 to 30 characters). Omit it after it is set.
idstring–The id of the thing to read or change: the project for "get" and "update", the objective for "update_objective", the key result for "update_key_result".
idsarray–For "remove": the prompt ids to set inactive. An id that is not on this brand answers not found and the others still go through.
impactinteger–Expected impact as a judgement: 1 low, 2 some, 3 clear, 4 high, 5 very high.
key_result_idstring–The id of the key result this project pays into. "list" returns the linkable ones in `key_results`; pass one of their `id` values. Omit for work that pays into nothing yet, which is exactly what the…
kindstring–Is this a project with an end, or recurring day-to-day work? Default "project".
linkedin_urlstring–Your LinkedIn profile, on linkedin.com.
manual_valuenumber–For key results: the current value typed by hand. Shown as typed by hand; prefer dataset_id + value_column.
objective_idstring–For "create_key_result": the objective it belongs to. "objectives" lists them.
ownerstring–The one person accountable for it.
parent_idstring–The project this one is part of. Projects nest at most three levels deep (programme, workstream, piece); a move that would make a fourth level or a loop is refused with a sentence. Parent progress, w…
progress_pctinteger–Progress in percent, 0 to 100, set by a person. Never derived from milestones or dates.
promptsarray–For "add": the prompts to store. Each item is {text, topic?, category?}. The server applies the brand rule per item and reports what it stored, what it reclassified and what it refused, with the reas…
resources_urlstring–A link to where the actual work lives (a drive folder, a board, a doc). http(s) only.
sortstring–For "list": the order of cards inside each group. "board" (default) puts off-track work first; "effort_impact" orders by impact (5 to 1) then effort (fewest days first), unrated work last. No combine…
spent_amountnumber–Money spent so far, typed by a person, in budget_currency.
stagestring–Where it stands. A new project starts "active" (running); when the board owner switched on "New projects need admin approval", a non-admin's new project starts at "inbox" (pending review) and only an…
started_atstring–Start date, YYYY-MM-DD.
starts_onstring–For objectives: start of the window its key results are paced against, YYYY-MM-DD.
statusstring–The traffic light, set by a person: on track, at risk, off track.
targetnumber–For key results: the number that counts as done. Required on create.
target_datestring–Target date, YYYY-MM-DD. "Due in N days" / "overdue by N days" is derived from it on every read and never stored.
target_reasonstring–For "update_key_result": why the target moves (ten characters or more). Required whenever `target` changes; the change is kept in the key result history.
titlestring–Project title. Required for "create".
unitstring–For key results: the unit the number is in.
value_columnstring–For key results: the column of dataset_id that holds the number.
website_urlstring–Your website, http(s).
x_urlstring–Your X profile, on x.com or twitter.com.

No output schema declared.

No examples provided.

apps ~1,558

Build a data app that runs on autario (HTML with the autario.js SDK on your own data), upload its code, set its manifest, save views, and publish or unpublish it.

NameTypeReqDescription
actionstringyesWhich operation to run. create = a new private app, needs name; upload_bundle = replace the app's HTML or files, needs app_id; update_manifest = name, datasets, shelf, sharing, needs app_id; write_ar…
app_idstring–upload_bundle, publish, unpublish: Id of an app you own, as returned by apps action "create". An app you do not own answers not found. update_manifest: The app id returned by apps action "create". wr…
artifact_idstring–Omit to CREATE. Give an existing artifact id to PATCH that one.
consumed_datasetsarray–What the app reads, e.g. [{"op":"datasetData","dataset":"<id>"}]. The sandbox bridge refuses any read the manifest did not declare. To read the connected accounts of whoever opens the app, add the co…
contentstring–create: The app's entry document when entry_kind is "upload": one HTML file, or index.html when you also send files. It runs in a sandbox with no outbound network: read autario data through autario.j…
content_typestring–create: Type of the uploaded content. Default text/html. upload_bundle: Type of content when it is the only file. Default text/html.
dataobject–Optional inline data belonging to the artifact.
datasetsarray–Ids of the user's OWN datasets (connector tables, uploads; get them from my_workspace action "overview") this app may read through autario.js. Everyone the owner shares the app with (role reader and…
datasets_ownedarray–Datasets the app OWNS and writes through autario.rows (insert, select, update, delete), e.g. [{"key":"contacts","title":"Contacts","scope":"app","columns":[{"name":"email","type":"text","required":tr…
entry_kindstring–"url" = the app already runs somewhere (give entry_url). "upload" = you are sending the app itself (give content or files). Default "url".
entry_urlstring–create: REQUIRED when entry_kind is "url". Must start with https://. update_manifest: Where the app runs. An uploaded bundle uses the conventional "index.html".
filesarray–A multi-file app: index.html plus every file it loads by relative path (e.g. "app.js", "css/style.css", "img/logo.png", "about.html"). Paths are relative, use "/", no "..". Allowed: html, js, mjs, cs…
namestring–create: Display name of the app, free text up to 80 characters; the same name as another app is fine. The returned app_id is the name lowercased plus a short random part and never changes on a rename…
shareobject–Let a report of this app be opened on a secret read-only link, e.g. {"subjects":["account"],"sections":["meta","report"]}. "subjects" says WHOSE data a link points at and may only name kinds autario…
shelfstring–The app store shelf the app sits on, one id: search, analytics, social, ads, commerce, financial_markets, banking_accounting, crm, productivity, developer, ai, public_data. Pick the one that matches…
source_urlstring–create: Optional link to the app's open source repository. update_manifest: Link to the open source repository.
specobject–The saved view/configuration as JSON (e.g. a Plotly spec, a filter set).
taglinestring–create: One line saying what the app does, max 200 chars. Worth writing: it is what a user reads in the app store, and an app cannot be indexed without one. update_manifest: One-line description, max…
tierinteger–Runtime model. 2 = sandboxed custom app (the default for anything you build here). Only set this if you know you need 1.
titlestring–Human title shown in the app and in my_workspace action "app_artifact".
typestring–Your own label for the kind of artifact, e.g. "chart", "report", "board". Required when creating.
versionstring–upload_bundle: Optional version label this bundle belongs to. update_manifest: Free-text version, e.g. "1.2.0". Bundles are stored per version.
visibilitystring–write_artifact: Who may read the artifact. Default private. publish: "public" = listed in the app store. "unlisted" = link only. Default "public".

No output schema declared.

No examples provided.

chart_instructions ~44

The builder spec reference for autario charts: chart types, required and optional fields per type, palettes, axis and annotation shapes, with examples. Charts render with Plotly.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

charts ~754

Create, publish and update interactive Plotly charts on autario.com from autario data, each with its insight text and cited sources.

NameTypeReqDescription
actionstringyesWhich operation to run. create_from_spec = a chart from a builder spec, needs builder_spec, dataset_ids; publish = a chart from a Plotly spec, needs title, dataset_ids; update = replace spec, title o…
builder_specobject–Structured Builder spec. Required: chart_type + x_col + y_col/y_cols (axis charts), label_col + value_col (pie/donut), x_col + group_by + value_col (heatmap). Optional: group_by, group_values, facet_…
chart_idstring–The chart ID or slug returned by charts action "publish"
dataset_idsarray–create_from_spec: UUID array of datasets backing this chart. Autario pulls real data from these tables. publish: Array of dataset UUIDs that this chart uses. Autario pulls real data from these datase…
insightstring–create_from_spec: 2-3 sentence data insight using ONLY numbers from get_data action "query"/find_data action "schema" results. Hallucinated numbers are rejected with the available anchor list. publis…
narrationstring–create_from_spec: Longer description (optional, defaults to insight) publish: Longer description of the analysis methodology and context update: Updated analysis description
plotly_specobject–publish: Plotly specification with traces array and layout object. Traces use x_col/y_col for column references and group_by/group_value for filtering (e.g. {"traces": [{"x_col": "year", "y_col": "va…
titlestring–create_from_spec: Chart title (also settable via builder_spec.title; this top-level wins if both set). Format: "{Topic} | {Scope} ({YYYY-YYYY}, {unit})". The YYYY-YYYY year range is REQUIRED whenever…

No output schema declared.

No examples provided.

delete ~197

Remove something the caller owns on autario: a dataset, all rows of a dataset, an app, or an accepted data edit. Cannot be undone.

NameTypeReqDescription
actionstringyesWhich operation to run. dataset = delete your dataset, needs dataset_id; rows = delete every row of your dataset, needs dataset_id; app = delete your app and its data, needs app_id, confirm; overlay…
app_idstring–Id of an app you own, as returned by apps action "create". An app you do not own answers not found.
confirmboolean–Must be true. A call without it deletes nothing.
dataset_idstring–dataset: The UUID of the dataset to permanently delete rows: The UUID of the dataset to clear all rows from overlay: The UUID of the dataset
idnumber–The overlay entry id

No output schema declared.

No examples provided.

find_data ~726

Search the autario catalogue of public statistics (World Bank, FRED, Eurostat, OECD, IMF, WHO, ECB, US Census, SEC) and your own connected datasets, and read a dataset's metadata and columns.

NameTypeReqDescription
actionstringyesWhich operation to run. search = keyword search over datasets; discover = datasets ranked for a topic by relevance, recency and source quality, needs topic; indicators = verified indicators that join…
categorystring–Filter by category. Options: "Finance & Economics", "Trade", "Technology", "Health & Society", "Energy", "Environment", "Demographics", "Education", "Infrastructure"
dataset_idstring–info: The UUID of the dataset to retrieve metadata for schema: The UUID of the dataset to get the schema for
depth_prefstring–Preferred dataset shape. "timeseries" for trend articles (daily/weekly/monthly/quarterly/yearly cadence), "cross-sectional" for snapshots (rankings, lists), "any" for no preference.
entity_typestring–Filter by entity_type: country | subnational | aggregate | company | security
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…
frequencystring–Filter by frequency: year | quarter | month | week | day
limitnumber–search: Maximum number of results to return (default 20, max 100) discover: Max datasets to return (1-50, default 10). indicators: Max results (default 50, max 500)
pagenumber–Page number for pagination (default 1)
publisherstring–Filter by publisher (World Bank, Eurostat, FRED, WHO, …)
querystring–Search term to match against dataset titles, descriptions, and keywords (e.g. "GDP growth", "CO2 emissions", "unemployment rate")
recency_windowstring–Filter by data freshness. Default "any" returns all datasets regardless of last_refreshed_at; tighter windows for time-sensitive articles.
searchstring–Full-text search across indicator titles + descriptions
topicstring–discover: The topic to find datasets for. Free-form, matches against asset topic field, title, keywords, category, and enriched description. Examples: "AI investment", "EU energy transition", "global…
unitstring–Filter by unit: USD | EUR | % | per capita | per 1000 | years | tonnes | tonnes CO2 | GWh | TWh | index | count | …
visibilitystring–Which datasets to search: "public" catalog only, "private" only your own datasets, "both". Default: "both" when authenticated, "public" otherwise. Other users' private datasets are never returned.

No output schema declared.

No examples provided.

get_data ~950

Read the numbers: rows of one dataset with filters and aggregates, or indicator values for countries and companies joined across sources (World Bank, FRED, Eurostat, OECD, IMF, SEC).

NameTypeReqDescription
actionstringyesWhich operation to run. query = rows of one dataset, filtered, sorted, grouped or summarized, needs dataset_id; entity_data = several indicators for one country or company over time, needs entity_id,…
aggregatestring–Comma-separated aggregations as "func(column)". Functions: avg, sum, count, min, max, stddev, median. Example: "avg(value),count(*),max(price)". Result columns are aliased as func_col (e.g. avg_value…
dataset_idstring–The UUID of the dataset to query
entitiesarray–Entity codes to compare (max 50). E.g. ["DEU","USA","CHN"]
entity_idstring–entity_data: Entity code (e.g. "DEU", "USA", "EUU") profile: Entity code (e.g. "DEU" for Germany, "USA" for United States, "EUU" for European Union, "WLD" for World)
fieldsstring–Comma-separated list of columns to return (e.g. "country_code,year,value")
filterarray–Filter conditions as "column:operator:value". Operators: eq, neq, gt, lt, gte, lte, like. Example: ["country_code:eq:USA", "year:gte:2000"]
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…
fullboolean–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.
groupbystring–Comma-separated columns for GROUP BY (only valid with aggregate). Example: "country,year". Use with aggregate to compute per-group statistics.
indicatorstring–Indicator ID to compare. Get from find_data action "indicators".
indicatorsarray–Indicator IDs (max 10). Get these from find_data action "indicators" or get_data action "profile".
limitnumber–query: Maximum number of rows to return (default 100, max 10000) profile: Max indicators to return (default 100, max 500)
non_null_onlyboolean–Drop rows whose value is null or storage junk (datasets are often mostly empty). Use to avoid wasting tokens on null rows. Default false.
offsetnumber–query: Number of rows to skip for pagination (default 0) profile: Pagination offset (default 0). When has_more is true, pass offset = previous offset + returned for the next page.
overlaystring–Which data: "source" (default) = exactly what the provider delivered; "with_overlay" = accepted derived columns, corrections and mappings merged in, each row with `_row_key` (use it in propose_*) and…
sortstring–Sort column and direction (e.g. "year:desc", "value:asc"). Aggregate aliases work too (e.g. "sum_value:desc")
summary_onlyboolean–Return only a finished per-column stats block (n, min, max, avg) plus first/last endpoint values, and NO raw rows. Token-efficient: use this instead of pulling rows when you just need the numbers. De…
timestring–entity_data: Optional time range, e.g. "2010-2023" or "2020". Format: YYYY or YYYY-YYYY compare: Optional time range: "2010-2023" or "2020"
topicstring–Optional: filter indicators by topic

No output schema declared.

No examples provided.

markets ~1,069

Public company and market data from SEC filings and live quotes (Yahoo): company snapshots and fundamentals, stock screens, investor portfolios from Form 13F, and US House member trades.

NameTypeReqDescription
actionstringyesWhich operation to run. snapshot = current quote and key metrics of one company, needs ticker; fundamentals = SEC fundamentals of one company over time, needs ticker; screen = daily stock screens by…
as_ofstring–YYYY-MM-DD: the newest daily snapshot on or before this day (for backtests). Default: the newest.
filtersobject–Column ranges, e.g. {"net_margin":{"min":10},"pct_vs_200w_ma":{"max":-20}}. A row without the column is excluded.
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…
intervalstring–Row spacing: the value known on the last trading day of each period. Default quarterly (token-efficient); daily for a backtest.
investorstring–Investor slug from markets action "investors" (e.g. berkshire-hathaway, scion-asset-management), its display name, or its SEC CIK.
limitnumber|integer–screen: Rows to return (default 25, max 200) investor_portfolio: Max holdings returned, largest first (default 500, max 5000). politician_trades, congress_trades: Max trades returned, newest first (d…
metricstring–avg_excess_since (default) | avg_excess_30 | avg_excess_90 | avg_excess_365 | hit_rate_30 | hit_rate_90 | hit_rate_365 | hit_rate_since | avg_return_since
metricsarray–snapshot: Metrics to return: price metrics (price, open, high, low, volume, perf_1d, perf_1w, perf_1m, perf_3m, perf_1y, perf_ytd, latest_date) and/or fundamental metric keys (e.g. revenue, roe, pric…
min_scoredinteger–Minimum scored purchases a member needs for a rank (default 5).
orderstring–asc | desc (default: best first)
partystring–R | D | I (only members in the current House carry a party).
politicianstring–Slug from markets action "politicians" (josh-gottheimer-nj) or a full or last name that matches exactly one member.
presetstring–growth | profitability | value | near-52-week-high | near-52-week-low | below-200-week-ma | most-held-by-13f
quarterstring–Quarter end date (2026-06-30) or label (2026-Q2). Omit for the latest reported quarter.
sortstring–Column to order by (default: the rank column of the preset)
tickerstring–snapshot: Stock ticker symbol, e.g. AAPL, MSFT, INTC, NVDA, SAP, BMW fundamentals: Stock ticker, e.g. AAPL, MSFT, KO who_holds: Stock ticker, e.g. AAPL, KO, GOOGL congress_trades: Stock ticker, e.g.…
windowstring–fundamentals: Time window: 1y, 3y, 5y, 10y, max, or from:to as YYYY-MM-DD:YYYY-MM-DD (either side may be empty). Default 5y. politician_trades: 30d | 90d | 1y | 2y | all (default 1y), by transaction…

No output schema declared.

No examples provided.

my_workspace ~552

What is on the caller's autario account and in the app store: apps, connectors (Google Ads, Meta Ads, Shopify, GA4 and more) with their health, charts, saved app views, and data edits waiting for review.

NameTypeReqDescription
actionstringyesWhich operation to run. overview = every app, connector and dataset on your account (sign-in); connectors = your connected platforms (sign-in); connector_status = freshness and report health of one c…
app_idstring–app_context: App id from my_workspace action "apps", e.g. "audience-360", "company-compare", "projects", "builder". app_artifact: App id from my_workspace action "apps", e.g. "audience-360", "project…
chart_idstring–The chart ID (numeric) or slug (hash like "nMGf-iAO") to retrieve
connector_idstring–The id of the connector instance (from my_workspace action "connectors").
dataset_idstring–The UUID of the dataset
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…
kindstring–Only this kind
limitnumber–charts: Maximum number of charts to return (default 20, max 100) overlays, proposals: Max entries (default 500)
offsetnumber–Number of charts to skip for pagination
qstring–Search term to filter charts by title or question
slugstring–Artifact slug from my_workspace action "app_context" / my_workspace action "overview" (your_artifacts[].slug).
statestring–Default accepted

No output schema declared.

No examples provided.

proposals ~336

Propose labels, flags, corrections and mappings on rows of the caller's datasets (Shopify orders, Google Ads campaigns, uploads) without touching the source, and accept or reject them.

NameTypeReqDescription
actionstringyesWhich operation to run. propose_column = a new label column, needs dataset_id, column, values; propose_flags = flag rows, needs dataset_id, rows; propose_corrections = corrected values for cells, nee…
columnstring–propose_column: New column name: lower case letters, digits and _, not an existing source column (e.g. "topic") propose_mappings: The source column whose values are mapped
correctionsarray–One entry per cell: {row_key, column, value, reason}
dataset_idstring–The UUID of the dataset
idsarray–accept: Proposal ids from a propose_* answer or my_workspace action "proposals" reject: Proposal ids
mappingsarray–One entry per source value: {source_value, value (the canonical value), reason}
reasonstring–Why, applied to every entry without its own reason
rowsarray–One entry per flagged row: {row_key, column? (a single cell), reason}
valuesarray–One entry per row: {row_key, value, reason?}

No output schema declared.

No examples provided.

refresh_connector ~90

Fetch the latest data from one of the caller's connected platforms (Google Search Console, Shopify, Meta Ads, Google Ads, GA4 and more) now and report per report what arrived. It never changes settings or the login, and runs at most once per connector per 10 minutes.

NameTypeReqDescription
connector_idstringyesThe id of the connector instance to refresh (from my_workspace action "connectors").

No output schema declared.

No examples provided.

report_data_issue ~361

Report a data-quality problem in an autario dataset or chart (World Bank, FRED, Eurostat, OECD, WHO, IMF, SEC or another publisher) with the observed numbers as evidence. A repeat of an open report is counted on the existing finding, never duplicated.

NameTypeReqDescription
dataset_idstring–The UUID of the dataset the issue is about (from find_data action "search" / find_data action "info"). Omit only for a chart-level issue with no single owning dataset.
detailstring–One-sentence human-readable summary of the issue.
evidenceobject–The concrete numbers backing the finding, as a JSON object. Examples: {"rows_seen": 500, "rows_expected": 15000, "source": "World Bank API has ~15k country-year rows"} or {"unit": "%", "value_range":…
finding_typestringyesWhat kind of problem. partial_ingest_suspected = fewer rows than the source has (truncated). stale = data older than it should be. broken_time_col = every row shares one date / a vintage column is us…
severitystring–How bad it is for end users. high = wrong/misleading numbers shown publicly. Default medium.

No output schema declared.

No examples provided.

social_publish ~189

Publish the caller's own approved social drafts on the caller's own connected X account or LinkedIn company page through the official APIs: list the channels, list the drafts, approve one draft, or post every approved draft now. A draft is never posted without approval.

NameTypeReqDescription
actionstringyestargets = the channels this account can post to; drafts = the social_drafts rows; approve = set one draft to approved (needs draft_id); run = publish every approved draft now, one per channel.
draft_idstring–approve only: the row id (dd_id) from drafts.
formatstring–Output wire format for this MCP call. Default 'toon' (Token-Oriented Notation, fewest tokens, best for tabular rows). 'compact' = minified JSON. 'json' = pretty JSON for readability. The REST API alw…

No output schema declared.

No examples provided.

write_data ~214

Create your own dataset on autario and append rows to it, private by default, readable through the same tools as World Bank or FRED data.

NameTypeReqDescription
actionstringyesWhich operation to run. create_dataset = a new empty dataset, needs title; write_rows = append rows to your dataset, needs dataset_id, rows.
categorystring–Category for the dataset (e.g. "Finance & Economics", "Health & Society", "Environment")
dataset_idstring–The UUID of the dataset to append rows to
descriptionstring–Description of the dataset contents, source, and methodology
is_publicboolean–Whether the dataset is publicly visible (default false)
rowsarray–Array of row objects where keys are column names (e.g. [{"country": "USA", "year": "2024", "value": "25000"}])
titlestring–Dataset title (e.g. "Global CO2 Emissions by Country")

No output schema declared.

No examples provided.

Install

How do I install the io.github.Autario/autario-mcp server?

io.github.Autario/autario-mcp is a hosted endpoint at https://autario.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · autario.com

# add to Claude Code
claude mcp add --transport http autario-autario-mcp 'https://autario.com/mcp'
Common questions

What is the io.github.Autario/autario-mcp server?

io.github.Autario/autario-mcp is listed in the public MCP registry as io.github.Autario/autario-mcp. Connect your ads, shop, analytics, social, CRM and finance tools, and let AI explain the numbers. This page covers its hosted endpoint (https://autario.com/mcp).

Is the io.github.Autario/autario-mcp server safe to use?

io.github.Autario/autario-mcp scores 66 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.Autario/autario-mcp server expose?

io.github.Autario/autario-mcp exposes 16 tools: find_data, get_data, analyze, markets, my_workspace, and 11 more. Their descriptions and schemas cost roughly 12,015 tokens of context every time the server is loaded.

Does the io.github.Autario/autario-mcp server require authentication?

No. We connected to io.github.Autario/autario-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the io.github.Autario/autario-mcp server still maintained?

io.github.Autario/autario-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the io.github.Autario/autario-mcp server?

VerifyMCP ran 13 checks on io.github.Autario/autario-mcp, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.