"Running queries in Apache Superset" matching MCP tools:

• searchA

  Website SpecA

  Read-only, deterministic full-text search across every spec page. Ranks pages by weighted keyword matches in title, slug, summary, and body, and returns the top results with status, category, canonical URL, Markdown URL, and matching body excerpts. No side effects and no live-web access — it queries an in-memory snapshot bundled at build time, so it returns in well under a millisecond. Use this for keyword/topic lookups when you do NOT already know the slug. Prefer `list_topics` when you want the complete, unranked set of pages matching a category/status filter; prefer `get_topic` when you already know the exact slug.

  ConnectorNo auth

• get_simulationA

  CrowdOSA

  Fetch the results of a study you ran, by id. Use it to read a study again, or to collect one whose tool call failed after the study launched: if a run tool returns error='timeout' or any error carrying recoverable: true, the study is still running (or has finished) and the error's sim_id names it. Do NOT re-run the tool — that launches and charges a second study. Wait 30-60 seconds, then call get_simulation(sim_id); poll again while status is 'running'. Returns the same shape as the run tool that started it, plus a top-level status (running | complete | failed | cancelled).

  ConnectorAPI key

• end_takeoverA

  Brix Digital SignageA

  End a running takeover or emergency on every screen it covers, in one call. When to use: - Taking down what start_takeover started, early. When NOT to use: - Changing default content: use set_screen_content. - Calling once per screen: one call ends it everywhere. What to know: - Screens return to their normal content at once. Ending one that already ended succeeds with alreadyEnded:true; an unknown id fails and lists what is running. Needs screen.cast (emergency-override.create for an emergency). Parameters: - castId: the castId start_takeover returned, an emergency id (emg_…), the id of the content on screen, or the takeover's exact headline. The last two end every running takeover of it. Find running ones with list_items kind casts or emergencies.

  Connector

  Destructive

  OAuth

• start_explorationA

  TestOptimA

  Explore the project's app so TestOptim learns new or changed pages and flows. Use it after adding pages, before start_test_run; tests for what it finds are generated and approved in the TestOptim app. Spends the plan's page allowance and replaces an exploration already running. Returns an exploration id - poll get_exploration, which takes minutes.

  ConnectorAPI key

• slack_channel_refresh_statusA

  Perspective AIA

  Wait on a Slack channel directory refresh that's already running for this workspace — read-only, never starts a new one. Use it to keep waiting after slack_channel_refresh returned "running". Returns "idle" when nothing is running. Behavior: - Long-polls up to wait_ms; returns "running" if still indexing (call again), "completed"/"failed" when it settles, or "idle" if no refresh is in progress. - After "completed" (or "idle"), use slack_channel_search / slack_channel_resolve to find the channel.

  ConnectorOAuth

• graphql_queryA

  stat-api — Sports DataA

  Run a GraphQL query against the same data with relations — nest from a game to its teams/players/odds in one call. Root fields are leagues (nfl, nba, …), each exposing its tables with the same filter arguments as REST plus `first`/`after` pagination. Do NOT send introspection queries (the schema is huge) — use describe_table instead; the SDL is at https://api.stat-api.com/api/v1/graphql/sdl. Requires a stat-api sign-in or API key; every row resolved anywhere in the tree counts against quota.

  ConnectorNo auth

• create_guidesA

  serpmanticsA

  Create new guides Create one or more new guides based on provided queries. Each guide targets exactly ONE engine and ONE analysis mode, chosen with the optional `source` field (default `google`). How to request each guide type: 1. Google SERP guide (1 credit per guide): omit `source`, or pass `source: "google"`. Example payload: {"queries": ["best crm"], "lang": "en-us"} 1bis. Google AI Overview guide (1 credit per guide). Two modes, like AI engines: `source: "google_ai_overview"` builds the guide from the TEXT of Google's AI answers (AI Overview, completed with AI Mode answers) ; `source: "google_ai_overview_citations"` builds it from the content of the web SOURCES those answers cite (recommended for GEO). Same language/country parameters as a Google SERP guide, 1 credit per guide in both modes. Example payload: {"queries": ["best crm"], "lang": "en-us", "source": "google_ai_overview_citations"} 2. LLM ANSWER guide (4 credits per guide): pass the engine name alone, e.g. `source: "chatgpt"`. The guide is built from the answer text the AI generates for the query. Example payload: {"queries": ["best crm"], "lang": "en-us", "source": "chatgpt"} 3. LLM CITATIONS guide (4 credits per guide) [RECOMMENDED AI mode]: pass the engine name with the `_citations` suffix, e.g. `source: "chatgpt_citations"`. The guide is built from the content of the web pages the AI cites in its answer. Example payload: {"queries": ["best crm"], "lang": "en-us", "source": "chatgpt_citations"} Which AI mode to pick? For GEO (getting a page visible in AI answers), prefer `<engine>_citations`: AI engines send traffic by CITING pages as sources, so the winning move is to look like the pages they cite. The answer-text mode (`<engine>` alone) is mostly useful to analyze how the AI phrases its own answer. When in doubt, pick `<engine>_citations`. The same two modes exist for every AI engine (chatgpt, perplexity, claude, gemini, grok, mistral, deepseek). To optimize the same page for several engines or modes (e.g. Google AND ChatGPT answers AND ChatGPT sources), create one guide per source value on the same query. IMPORTANT, HOW TO READ THE RESPONSE OF THIS ENDPOINT, WHICH SPENDS CREDITS. Queries listed in `guidesFailed` are PROVEN not to have produced a guide and their credit was given back (unless the account has unlimited credits, where nothing was reserved): re-sending them is free and correct. Queries listed in `guidesUnknown` have an UNDECIDABLE outcome and their credit is deliberately KEPT, because the guide was most likely written: DO NOT re-send them, you would pay for the same guide twice. Look them up in `GET /api/v1/guides` after a few minutes instead, and contact support if nothing shows up. Finally, a `200` is NOT a promise that every query produced a guide: compare `guides.length` with the number of queries you sent, never read `success` alone, and never re-send a query just because it is missing from `guides`.

  ConnectorNo auth

• get_jobA

  Tomorrow Central: Cloud Cost SentinelB

  Check the status of a Tomorrow Central job. Poll this after starting any scan. Status goes QUEUED → RUNNING → COMPLETED (or FAILED). A typical scan takes 1-3 minutes. The response's `poll_after_seconds` field is the minimum wait before polling again — respect it. Never start a second scan while one is RUNNING; the platform coalesces duplicates onto the in-flight job anyway (`coalesced: true`), and rate-limit errors include `retry_after_seconds` telling you exactly how long to back off.

  ConnectorNo auth

• nevent_switch_tenantA

  Nevent MCPA

  Switch the active tenant for this session. All subsequent queries (analytics, segments, campaigns, paid media) will use the specified tenant's data. SUPERADMIN: this mutates your user record in the database — the switch PERSISTS. Always call nevent_reset_tenant when cross-tenant work is done to avoid leaving your account pointing at another tenant. OWNER/ADMIN/STAFF: session-scoped only; you can only switch to tenants in your hierarchy subtree (max 3 levels deep). Use nevent_list_tenants to discover available tenant IDs.

  ConnectorNo auth

• get_edit_runA

  Extend MCPA

  Get the state and output of an edit run (edit group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry. Edit runs have no list endpoint — keep the run ID. While status is "running", call again with wait: true (same workspaceId and environment) until it is terminal; never re-submit the document. On UNAUTHORIZED or NOT_FOUND, re-call get_me for the granted targets. output.editedFile.presignedUrl expires in ~15 minutes (re-fetch with get_file). Output shape is documented at https://docs.extend.ai/editing/response-format.md (get_documentation).

  ConnectorOAuth

• get_audit_reportA

  The Service Marketing Guys AuditA

  Fetch the status and, when finished, the report for a runId returned by check_site_speed, check_ai_visibility, check_local_rank, or start_audit. For a running result, wait pollAfterSeconds, then call again with the same runId. Repeat while status is running.

  ConnectorNo auth

• start_auto_clusteringA

  MencoroA

  Start a background job that proposes how to group up to 500 tracked queries into clusters. mode "fill_gaps" places only queries that have no cluster yet; "add_on_top" adds clusters without touching existing memberships; "full_regroup" proposes a fresh grouping of every query. restrictToExistingClusters only uses the project's current clusters. Nothing changes until apply_auto_clustering: poll get_job, show the proposal to the user, then apply it. Requires an active subscription.

  ConnectorOAuth

• update_alertA

  Costory: Your Finops MCPA

  Update an existing cost alert. Look up alertId via search / list_alerts / get / create_alert. All fields except alertId (and slug) are optional — omit a field to keep the stored value. Most edits (name, description, tagIds, condition, dedup) need nothing else. `tagIds` replaces the full list: existing IDs from list_tags and/or `{ name, color? }` for new tags; color defaults to #6366F1; missing tags are created. Omit keeps stored tags; `[]` clears them. Explorer (`queries` + period) and notification dest are wholesale groups: if you send any field in the group, send the full group, written from scratch exactly as for create_alert — the stored `queries` from get are not a valid input. Inside the explorer group, omit `scopeId` to keep the alert's saved scope (send null to clear it); it cannot be sent on its own. `scopeId` is the same id as list_teams, stored on the alert (read it from get) and not merged into the stored queries. Do not send `aggBy`: the stored grain is always Day. Setting `condition` on a legacy threshold alert that has no dedup config succeeds but the response may include `warning`: pass `dedup` too (or in a follow-up call) to avoid notifying on every firing evaluation. Sharing is not this tool — use get_object_permissions then set_object_permissions with resourceKind "costAlert". `messageWidgets` replaces the message-widget list wholesale (exactly one ALERT widget required; no DIGEST on alerts); omit to leave the stored widgets unchanged. To edit, read the current list via get: each entry carries `config`, a lossless writable copy in the exact shape this field accepts — echo every `config` you are NOT changing back verbatim and edit only the entries you mean to change, so untouched widgets keep their full stored settings (the prose `parameters` summary is truncated and NOT writable). If any entry's `config` is null, its stored settings cannot be expressed here — do not replace `messageWidgets` then. EXAMPLE: rename → { alertId, name: "New name" } EXAMPLE: dest switch to Slack → { alertId, notificationChannel: "SLACK", slackChannelId: "C01ABC" } EXAMPLE: condition change → { alertId, condition: "a > 2000" } EXAMPLE: narrow the monitored series (scope kept) → { alertId, queries: [{ type: "cost", name: "a", metricId: "cost", currency: "USD", filterCel: "cos_provider in [\"AWS\"]" }], datePreset: "TRAILING_90_DAYS" }

  Connector

  Destructive

  OAuth

• get_ai_recommendation_resultA

  AI Recommendation CheckA

  Use this to read the result of a check started with check_ai_recommendation, using the check_id it returned. Returns the status (queued, running, done, failed or refused). When done: for ChatGPT, Perplexity and Gemini, how many of their answers named the business, which businesses they named instead, and one fix. While a check is queued or running, poll_after_s is the suggested wait in seconds before reading it again. It waits up to about 20 seconds for a running check to finish. It does not start a new check.

  ConnectorNo auth

• get_bing_query_statsA

  SEO GSC Wizard MCPA

  Use this when the user asks which Bing searches bring them traffic. Top Bing Webmaster Tools queries for a property, aggregated across the window (clicks, impressions, CTR as a 0-100 percentage, and impression-weighted average position). Not for Google queries: use query_top_queries; for one page use get_bing_page_queries. Bing reports only its top queries, dated by week: a window selects whole weeks, and the rows do not sum to get_bing_traffic_stats totals. Rows are sorted by clicks, then impressions, highest first. `rowCount` counts the rows returned (at most `limit`), `totalRows` the distinct queries Bing reported before that cut. Returns notConfigured: true when no Bing Webmaster API key is set up for the property.

  ConnectorOAuth

• parse_phone_numberA

  TanodA

  utilpeek: parse and format a phone number. For a prefix's country and network use lookup_phone_prefix. A string that is not a phone number, or a national form without region, is a 422 (not charged). Offline numbering-plan check (phonenumbers, Apache-2.0): `valid` means the number fits its country's numbering plan, not that it is assigned, in service or reachable; `carrier` is the original range holder (ported numbers are not detected). The submitted value is processed in memory only, never logged or stored. Typically under 0.1 s. Price: USD 0.001. Free: 10 utilpeek calls per IP per UTC day. Docs: https://tanod.dev/learn/phone-number-validation-api.html

  ConnectorNo auth

• parse_phone_numberA

  Developer Utilities & Validators (Tanod)A

  utilpeek: parse and format a phone number. For a prefix's country and network use lookup_phone_prefix. A string that is not a phone number, or a national form without region, is a 422 (not charged). Offline numbering-plan check (phonenumbers, Apache-2.0): `valid` means the number fits its country's numbering plan, not that it is assigned, in service or reachable; `carrier` is the original range holder (ported numbers are not detected). The submitted value is processed in memory only, never logged or stored. Typically under 0.1 s. Price: USD 0.001. Free: 10 utilpeek calls per IP per UTC day. Docs: https://tanod.dev/learn/phone-number-validation-api.html

  ConnectorNo auth

• save_queryA

  SaturnSQLA

  Save SQL to the query library, or overwrite one of your own saved queries by passing its id. Use it when the user wants to keep, reuse or schedule a query; pass the returned id to run_saved_query or create_schedule. Does not run the SQL, so test it with execute_query first. A new query is private to you until shared in the app. Passing an id replaces that query's name, SQL, connection and folder; you can only update queries you created. Needs the write scope, plus execute to change the SQL of a scheduled query.

  Connector

  Destructive

  API key

• cancel_executionA

  AnkraB

  Cancel a running platform execution (a deploy, sync, or other operation from list_recent_executions). A mid-flight cancellation can leave the affected resource between versions until the next reconcile; prefer letting a deploy finish and rolling back unless it is actively harmful. Not running executions answer their settled state unchanged.

  Connector

  Destructive

  OAuth

• bulk_resume_monitorsA

  FettleA

  Resume up to 100 paused monitors in one call, all or nothing; each goes back to PENDING and is checked on the next tick. For one monitor use resume_monitor; to run a check right away on a monitor that is already running, use check_now. Requires a key with the write scope. Resuming more monitors than the plan's active limit allows is a 403 and nothing changes (see get_plan_usage). A monitor already running is left as it is. Returns monitors: the list_monitors rows after the change, in request order. Example: {"monitor_ids": ["<id from list_monitors>", "<id from list_monitors>"]}

  ConnectorOAuth

• seo_reportA

  SEO SkillA

  Start here. Without site: a short summary of every site in the person's weekly site audit (beta) for last week, with each site's Google index, weekly crawl and search clicks, sites with changes first, ending with the site to ask about next; an account outside that beta gets its site list to pick from. With site: the main report for that Search Console property, the overview plus each section's row count and top rows. With site and section: that section's rows; page sections also check their top 20 URLs live. Sections: - overview: Site totals (clicks, impressions, CTR, position) against the previous period, by device, with the top pages and queries and their change, and Google Analytics sessions for the same dates from the property whose web stream matches the site. - quick-wins: Query and page pairs at average positions 4 to 10 with a click-through rate below the site’s own curve for that position. - low-ctr: Query and page pairs at average positions 1 to 4 with a click-through rate below the site’s own curve: titles and snippets to review with the person. - striking-distance: Queries just outside the top positions, with impressions, for pages that already rank. - second-page: Pages with an average position of 11 to 20 and their queries. - content-decay: Query and page pairs that lost clicks against the previous period. - cannibalization: Queries where more than one page of the site gets impressions, with each page’s share. - traffic-drop: Daily clicks and impressions checked for a sudden change that lasted, with the date it started (else the last 7 days against the days before), and Google updates within 3 days of that date. Overlap is timing only, not cause. - ai-queries: Queries with the shape of AI conversations and agent searches (replies such as "yes go on", follow-ups, agent prompts, search operators, chat phrasing, ten or more words), with rewordings grouped into one question and its top page, impressions, clicks and position. A heuristic: Search Console does not mark AI Mode. - bing: Bing’s top queries from Bing Webmaster Tools with Google’s clicks, impressions and position for the same query beside them, and the same for pages. - issues: A list kept for the site between sessions: issues the striking-distance, low-ctr and quick-wins checks found (and the weekly crawl and Google index checks for an audited site), each with its id, the latest check and what the person marked it (open, fixed or ignored). Asking for it runs those checks again. To mark issues, add mark and issues instead of section. The hosted server keeps the list only for sites in the weekly site audit; for any other site it returns the list as JSON for the agent to save and pass back as saved. With site, mark and issues: records what the person decided about those issue ids (fixed, ignored, or open to undo) and runs no checks.

  ConnectorOAuth