Skip to main content
Glama
619,939 tools. Updated 2026-09-28 21:07

"Sumo Logic" matching MCP tools:

  • Validate whether a component will work within your operating conditions. Compares your design parameters against the datasheet's absolute maximum ratings and recommended operating conditions. Returns PASS/FAIL/WARNING per parameter with margin percentages. Parameter mapping by component type: - Buck/boost converters: input_voltage, output_voltage, output_current, ambient_temp - MOSFETs: supply_voltage=VDS, output_current=ID (drain current), ambient_temp - LDOs: input_voltage, output_voltage, output_current, ambient_temp - Logic ICs: supply_voltage=VCC, ambient_temp Result semantics (per-parameter 'result' field): - PASS: comfortable margin. For a recommended-operating RANGE, any value inside the range (including the exact edges) is PASS. For an absolute-MAX rating, PASS means more than 10% below the limit. - WARNING: for absolute-max ratings only, the user value is within 10% of the limit (but not over) — part will work but with thin margin for part-to-part variation, temperature drift, and transients. Consider derating. - FAIL: user value is outside the allowed range / exceeds the limit — part is out of spec and will be stressed or damaged. - INSUFFICIENT_DATA: the check could not be completed safely — most commonly an ambient_temp input that could not be translated to a junction-temperature check (see the temperature note below). INSUFFICIENT_DATA never counts as a PASS: it pulls the overall verdict down to at-least-WARNING. Each check also reports 'limit_type' (max / min / range / fixed) so you can see whether it was judged against an operating range, an absolute-max rating, or a fixed-output setpoint. Temperature honesty: - ambient_temp is NOT silently treated as a junction temperature. The stored operating-temperature limit is junction-suspect, so a bare ambient input is never reported as a clean PASS on thermal grounds. If you also supply input_voltage, output_voltage and output_current AND a thermal-resistance (RthJA) value is available, the tool estimates Tj = Ta + Pd·RthJA (Pd ≈ (Vin-Vout)·Iout, a documented approximation) and checks the junction estimate — reported as 'temperature (junction est.)' with the assumptions in the note. Otherwise the temperature check returns INSUFFICIENT_DATA asking you to pull RthJA via read_datasheet. The 'temperature_basis' field (junction / ambient / unknown) tells you which basis was used. Behavior: - Two-tier validation. For parameters in our structured database (Vin, Iout, operating temp, etc.), returns instantly and free of LLM cost. For parameters only found in the datasheet text, falls back to an LLM read of the absolute-max and recommended-operating-conditions sections. The 'validation_method' field in the response tells you which path was used. - If the part hasn't been extracted yet and the LLM fallback is needed, this call triggers extraction (30s-2min). Returns status='extracting' if so — poll check_extraction_status and retry. When NOT to use: - You need power dissipation or junction-temperature rise — this tool only checks nameplate limits. Pull RthJA from read_datasheet and calculate yourself. - You need SOA (safe-operating-area) curve checks for MOSFETs — use analyze_image on the SOA graph. - You're checking a passive or mechanical part with no abs-max table — there's nothing for this tool to compare against. Example: check_design_fit('TPS54302', input_voltage=24, output_current=2.5, ambient_temp=70)
    ConnectorNo auth
  • Set the caller's inbox_mode + (for 'quiet') inbox_quiet_min_karma. Mirrors ``PATCH /me/inbox``. The recipient-side opt-out for cold DMs — the natural counterpart to ``colony_get_cold_budget`` which tells you your sending budget. Modes: * ``open`` (default) — accept cold DMs from any sender past the platform floor. * ``contacts_only`` — accept only warm threads + peers you have messaged first. * ``quiet`` — accept only from senders whose karma clears ``inbox_quiet_min_karma``. The threshold is REQUIRED when mode is ``quiet`` and is cleared to NULL when mode flips to anything else (a stale value would confuse the receiver opt-out logic in Phase 3). Stored Phase 1; enforced in Phase 3 (THECOLONYC-106). Idempotent — posting the same mode twice is a no-op. Response shape mirrors the REST endpoint: { "inbox_mode": "quiet", "inbox_quiet_min_karma": 5 }
    ConnectorNo auth
  • Set the caller's inbox_mode + (for 'quiet') inbox_quiet_min_karma. Mirrors ``PATCH /me/inbox``. The recipient-side opt-out for cold DMs — the natural counterpart to ``colony_get_cold_budget`` which tells you your sending budget. Modes: * ``open`` (default) — accept cold DMs from any sender past the platform floor. * ``contacts_only`` — accept only warm threads + peers you have messaged first. * ``quiet`` — accept only from senders whose karma clears ``inbox_quiet_min_karma``. The threshold is REQUIRED when mode is ``quiet`` and is cleared to NULL when mode flips to anything else (a stale value would confuse the receiver opt-out logic in Phase 3). Stored Phase 1; enforced in Phase 3 (THECOLONYC-106). Idempotent — posting the same mode twice is a no-op. Response shape mirrors the REST endpoint: { "inbox_mode": "quiet", "inbox_quiet_min_karma": 5 }
    ConnectorNo auth
  • Apply a list of structured edit ops to an existing Mermaid `source` and return the edited diagram. This is the declarative counterpart to `execute`: plain JSON in, plain JSON out, no sandbox. Prefer it for straightforward edits; reserve `execute` for logic the ops don't express. Returns { ok, family, source, verify:{ ok, warnings } } on success, or { ok:false, family, opIndex, error } — where `error` names the offending field and lists the valid ones — when an op is malformed or cannot apply. Ops apply in order and are all-or-nothing: the first failing op stops the batch (its position is `opIndex`) and the input is left untouched. Each op is { "kind": <op>, …fields }. Call `describe_sdk` for the detected family before authoring unfamiliar ops; it returns compact signatures or exact field types, enum values, defaults, and constraints.
    ConnectorNo auth
  • Get SEC Form 4 insider-trading activity — per-ticker detail or S&P 500 screener. Surfaces already-ingested Form 4 filings (the same Form 4 feed behind the market model's `form4` stage) pre-chewed into analytical context so you don't have to parse raw XBRL yourself: buyer role (officer / director / 10% owner), transaction size vs that SAME insider's own historical buy pattern (`size_vs_own_median`, `is_unusually_large` when >=2x their own median), and cluster-buy detection (`is_cluster` — 3+ distinct insiders buying the same ticker within a 10-day window, historically the stronger signal vs a single insider's trade). Every transaction links to its source SEC filing via `accession_url` — verify anything before acting. Two modes: - ticker set: per-ticker view — up to 40 most-recent Form 4 transactions over the trailing year plus `cluster_buy_active`. - ticker omitted: S&P 500 (top-100) screener — tickers with a cluster buy or an unusually-large buy in the last 30 days. An empty `results` list is a valid, honest answer; most weeks most tickers show nothing notable. Read-only surfacing: this is information, NOT a buy/sell recommendation, and it does NOT feed the quantum model's conviction/verdict logic — insider clusters are a candidate signal still pending backtest validation. Args: ticker: Optional. Stock ticker for the per-ticker view (e.g. "AAPL"). Omit for the S&P 500 screener. Case-insensitive. Returns per-ticker: ticker, transactions, cluster_buy_active, generated_at, disclaimer. Screener: tickers_scanned, results, generated_at, disclaimer.
    ConnectorNo auth
  • Companies most similar to a given one - optionally ACROSS THE BORDER. Read-only. Parameters: - company_id (required): "AT:{fnr}" or "DE:{court}_{type}{number}" (bare national ids accepted), from a search card. - n (optional, default 10): how many peers per country. - cross_border (optional, default false): when true, additionally returns ``peers_abroad`` - the companies in the OTHER country whose registered purpose is semantically closest to the reference company's activity text. Returns {company_id, country, peers_home, home_envelope, peers_abroad?, notes}. ``peers_home`` uses the home register's own peer logic (AT: same size class, same industry preferred, nearest by Bilanzsumme; DE: semantic-first by registered purpose). ``peers_abroad`` is a MEANING-based match, not a size or financial benchmark - the honest cross-border comparison given the countries' different data depth (see notes). Empty peers_home means the id is unknown or the company lacks the data its register ranks by. For a strict filtered list use search_companies; for aggregates use the country server's cohort tools.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    MCP server for Sumo Logic — 37 tools for searching logs, managing monitors, alerts, dashboards, collectors, and metrics. Zero hardcoded org-specific values.
    48
    1
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Enables searching Sumo Logic logs using the search_logs tool, with support for query parameters such as time range and maximum results.
    1
    1
    -

Matching MCP Connectors

  • Micro-settled web content extraction and JSON schema validation utilities for AI agents and MCP clients, backed by the Bristlecone Logic API engine.

  • Search 200M+ patents and scientific literature in natural language using PatSnap's global R&D intelligence database.

  • Create a form, define its fields, brand it, publish it, and return a shareable short link + QR in one step. Use for 'make me a form to collect X, give me a link and QR to share it'. The result's `share_url` is the public link and `qr_id` is the form's own dynamic QR code (image included) — never call create_qr_code or create_short_link for a form's link; pass QR design args (primary_color, eye_style, frame, logo_url, …) here to style that code in the same call. Supports on-brand styling (theme/colors/logo), a `redirect_url` after submit, conditional logic (`show_when` on a field) and branching endings (`outcomes`), and a custom domain/slug. Publishing mints a dynamic short link and QR — always dynamic, no static option, since a form has to resolve somewhere live. Notifications are a separate, paid, verified-member setting. To change a form later, use update_form.
    ConnectorOAuth
  • Account-level statistics and channel breakdown for a timeframe. USE FOR: General account stats by period, channel breakdown, high-level metrics (ROI, spending, leads, opportunities), custom date ranges. NOT FOR: Campaign-level info (use experiment_performance_stats), specific experiments (use get_experiments). CHANNELS: FACEBOOK, LINKEDIN, GOOGLE ADS, ALL TIMEFRAME LOGIC: - 'quarter'/'Q1-Q4' → timeframe='QUARTER' - 'week'/'weekly' → timeframe='WEEK' - ≤3 months → timeframe='MONTH' - >3 months → timeframe='QUARTER' - Default: timeframe='MONTH' CUSTOM DATE RANGE: Provide ONLY startDate + endDate (NO timeframe). Format: ISO 8601 (YYYY-MM-DDTHH:mm:ss.sssZ) NO DELIVERY: a period with no delivery comes back with empty totals and an empty channelBreakDown (the platform sends null for both); read that as zeros for every channel, not as missing data. METRICS: impressions, clicks, spent, leads, mqls | opens, sends, actionClicks (CONVO/MESSAGE ads) | triggeredOpps, triggeredOppsAmount, influencedOpps, influencedOppsAmount | triggeredClosedWonOpps, triggeredClosedWonOppsAmount | roiInfluencedOpp, roiTriggeredOpp | cpc, cpl, cpm, ctr, conversionRate | costPerOpen, costPerSend (CONVO/MESSAGE ads) | customFields array CONVO/MESSAGE AD CAVEAT: opens, sends, actionClicks (and their per-cost derivatives) are the success metrics for CONVO and MESSAGE (LinkedIn message) ad types. clicks/ctr/cpc are typically 0 for these ads — do not treat that as "no performance". If account-level data shows high spend with 0 clicks, drill into experiment_performance_stats or get_ad_details to confirm ad type before drawing conclusions.
    ConnectorAPI key
  • For apps that cannot connect the Rhylthyme account directly: returns a sign-in URL, then accepts the pasted token. Only the user's own saved programs, runs and imports need it; everything public works without. Tokens last about an hour.
    ConnectorNo auth
  • A game kit IS an engine: its manifest carries asset slots AND GameRules — the genre as a document (movement, camera, world, objective, entities, pickups, ai, hud, audio). action=list → kits of the workspace. action=get {id} → manifest + rules (lib_… id). action=create {style?, name?, rules?, slots?} → new kit, rules default to the style then merge yours. action=patch {id, rules?, slots?, prompts?, name?} → partial update; rules merge section by section, a section set to null resets it. Slot refs inside rules must point at slot ids of the kit (unknown refs are dropped, the renderer falls back to procedural). Compose a NEW genre by writing rules: e.g. movement vehicle-boost + world arena-ring + objective knockout = sumo cars, no code.
    ConnectorNo auth
  • Edit a form draft’s logic in place: `upsert` replaces each calculation whose `id` matches an existing one (and appends the rest as new), `remove` deletes calculations by id — every other calculation is preserved byte-for-byte. Prefer this over update_form_logic whenever the form already has logic: it sends only the diff and cannot drop calculations you did not mention. Calculation shape, effect operators and expression syntax are exactly update_form_logic’s (see its description), and upserted calculations are validated the same way before anything saves. Get current ids from get_form_logic; a calculation stored without an id can only be edited through update_form_logic. Requires form:write.
    Connector
    Destructive
    API key
  • Find movies and/or TV shows that are genuinely available on a subscription streaming service in a specific country, filtered by score, genre, runtime, age rating, release year, country of origin, required cast members, notable people's own watch history, review tone, and similarity to a title the user already knows. All given filters combine with AND logic (except where noted). Use this instead of guessing streaming availability from general knowledge, which is frequently wrong or outdated -- catalogs change constantly and vary by country. Also use this tool for completely open-ended requests with no stated criteria at all, e.g. "suggest something to watch" or "I don't know what I want to watch" -- call it with just the country and no other filters to get QQuickPick's currently popular streamable picks, rather than answering from general knowledge alone. Movie results also carry a "facts" object (or null when unknown): Best Picture winner/nominee, Oscars won ("at least" -- the source is not exhaustive, so never state it as an exact count), festival top prizes, the work it is based on, and its franchise with all films in order. Use the awards / based_on_existing_work / franchise filters (movies only) to answer questions like "Oscar winners based on a novel I can stream tonight" or "all films of a franchise available to me". Use similar_to for "something like X" requests instead of guessing similar titles from general knowledge. Use origin_countries for requests like "an Asian film" or "a French series" -- do not guess specific titles from general knowledge for this. Each result includes a site_url (QQuickPick detail page) and, where available, a watch_link with required attribution -- include these links when presenting results to the user, not just the raw facts. The response also carries a top-level available_filters hint listing filters on this tool that were not used in this call -- consider offering ONE of them as a natural follow-up question, not all of them, and only when it fits the conversation.
    ConnectorNo auth
  • Returns the user's default workspace (id, uniqueName, name, description) so you can use it as the `workspace_id` argument for other tools without prompting. Behavior: - Read-only. Takes no parameters. - Picks the default by priority: explicit user default > first owned workspace with activity > invited workspace. Same logic the web app uses to auto-select. - When no workspace is reachable, returns an object with null fields (does NOT error). This happens when the user has no accessible workspaces (owned or invited), or when a workspace-scoped session reaches none of the user's workspaces. - A brand-new account that has not finished setting up also gets an `onboarding_url`. Relay that link and wait for the user to confirm they finished before retrying. When to use this tool: - Start of a conversation when the user hasn't named a workspace — avoids asking which one to use. - Whenever you need a `workspace_id` and the user implied "my workspace" or didn't specify. When NOT to use this tool: - The user names a specific workspace — use workspace_list to find it by name. - You already have a `workspace_id` and just want its details — use workspace_get. - Enumerating every accessible workspace — use workspace_list.
    ConnectorOAuth
  • Market Intelligence — the freshest SOURCED semiconductor market briefs, generated daily from a Tavily + Claude scan of primary press, earnings, and trade outlets. Each brief returns title, severity (Critical/High/Medium/Low), confidence_score (0-100), quantitative_impact (e.g. "Est. BOM increase: +$500"), an executive summary, a short analysis, a category (Logic/Memory/Packaging/Connectivity/Power/Geopolitics), and a curated sources[] list — plus per-record provenance. UNIQUELY: each brief also carries `entities` (the chips/nodes/packaging/HBM-gen/companies it concerns), `impact` (when it's a cost move, the per-chip BOM dollar deltas computed from Silicon Analysts' cost models — e.g. "HBM +20% → +$580 on B200" with a pre-filled calculator URL), `related` (cross-links to the live datapoints + tools), and `novelty` (when the HEADLINE fact first became public as the scanner could VERIFY it — verdict fresh/dated/stale/unknown, the verified first_public_date + source, and dataset_match when the figure was already in Silicon Analysts' data, i.e. the brief is a recap; a Critical is only ever stored when the fact is verifiably ≤7 days old). No pure-news source does this. The machine feed returns ALL severities; `published` flags the Critical/High briefs that also have a public page. Public sources only; no insider data. USE THIS for: "what's the latest in HBM / CoWoS / TSMC supply this week?", "any recent semiconductor price hikes, yield news, or capacity moves?", building a sourced market-news digest, grounding a claim about a recent supply-chain event. DO NOT USE for: current absolute cost/pricing values (use get_accelerator_costs / get_wafer_pricing / calculate_chip_cost); structured data movements over time (use get_recent_changes); allocation/lead-time status (use get_foundry_allocation). Filters: severity, category, since (ISO timestamp), publishedOnly (bool), limit (1-100, default 25). N2/Apple omitted (conflict-safe). Cite as "Silicon Analysts — Market Intelligence".
    ConnectorNo auth
  • Smart supplier recommendation based on sourcing requirements. USE WHEN: - User describes what they need: "I need a factory for cotton t-shirts in Guangdong" - User asks for recommendations, not just search results - "who's the best factory for [product]" - "recommend a top supplier for my [product] line" - "shortlist 5 suppliers for [product] in [province]" - "best own-factory (not broker) for [product]" - "give me the top [product] manufacturer" - "which factory should I go with for [product]" - "推荐供应商 / 帮我找合适的工厂 / 最好的 [品类] 厂" - "帮我排个优先级 / 推荐几家最好的" - "我想做 [品类],给我推荐几家工厂" WORKFLOW: Entry point for "I need help finding a supplier" requests. recommend_suppliers → get_supplier_detail (vet top pick) OR compare_suppliers (evaluate top N side-by-side) OR check_compliance (verify export readiness of top pick) OR find_alternatives (expand the shortlist). DIFFERENCE from search_suppliers: search_suppliers FILTERS by exact criteria (province, type, capacity). This tool RANKS by fit — prioritizes own-factory, then quality score, then capacity. DIFFERENCE from find_alternatives: find_alternatives starts from a KNOWN supplier_id and finds similar ones. This tool starts from product REQUIREMENTS. RETURNS: { query, total_matches, showing_top, note: "ranking logic", data: [supplier objects] } EXAMPLES: • User: "Recommend me the top 5 factories for sportswear in Fujian" → recommend_suppliers({ product: "sportswear", province: "Fujian", type: "factory", limit: 5 }) • User: "I need the best own-factory (not trading company) for down jackets" → recommend_suppliers({ product: "down jacket", type: "factory", limit: 5 }) • User: "帮我推荐 3 家广东做 T 恤的工厂" → recommend_suppliers({ product: "t-shirt", province: "Guangdong", limit: 3 }) ERRORS & SELF-CORRECTION: • Empty data → try in order: (1) drop province, (2) drop type filter, (3) broaden product (e.g. "compression leggings" → "activewear"), (4) fall back to search_suppliers for filter-based view. • product_type not found in normalizeProductType → use the Chinese term or the parent category. • Rate limit 429 → wait 60 seconds; do not retry immediately. • Empty after 3 retries → tell user: "I don't see verified suppliers matching [product] in [province]. Want me to broaden to nationwide, or try a sibling category?" AVOID: Do not call this when the user wants exact filtering — use search_suppliers. Do not call repeatedly for different limit values — request max once then slice in your response. Do not use for cluster recommendations — use search_clusters. NOTE: Ranking: own_factory > quality_score > declared_capacity_monthly. Source: MRC Data (meacheal.ai). 中文:基于采购需求智能推荐供应商,按 自有工厂 > 质量分 > 产能 排序。
    ConnectorNo auth
  • PRE-ACTION Bulk Processing ($0.10). Evaluates a list of items in one call; each item is a dict shaped {"response": str, "policy"?: str}, where policy defaults to "default" if omitted and may be any built-in policy name (default, strict, anti_jailbreak, safety, content_quality). Each item gets its own independent COMMIT/NO_COMMIT verdict via the same logic as the matching single-item evaluate_* tool; results are returned in input order under `results`, plus a shared `batch_id`. Capped at 200 items per call — oversized batches are rejected. Use this instead of multiple single-item evaluate_* calls when checking several responses — optionally against different policies — in one priced call rather than paying per item separately.
    ConnectorNo auth
  • Granular performance metrics for ads, audiences, creatives, offers, target groups, keywords. IMPORTANT: Always specify endpoint parameter. Always use ISO 8601 for dates. USE FOR: Best performing ads/audiences/creatives/offers/target groups, ingredient comparisons, ad type analysis (IMAGE, VIDEO, CAROUSEL), lead gen forms vs landing pages, pipeline by ingredient, creative previews, keyword performance. NOT FOR: Account-level stats, experiment-level analysis without ingredient focus. ENDPOINT LOGIC: - 'target group' → customAudience/group - 'audience' → customAudience - 'offer'/'lead gen'/'landing page' → offer - 'creative' → creative - 'keyword' → keywords - 'ad'/'ads' or default → ads AD TYPES: IMAGE, VIDEO, CAROUSEL, DOCUMENT, CONVO, SPOTLIGHT, SEARCH, MESSAGE - The `adFormat` field on each response row identifies the ad type. METRICS: spend, impressions, clicks, leads, mqls | opens, sends, actionClicks, costPerOpen, costPerSend (CONVO/MESSAGE ads) | cpl, cpc, cpm, ctr, conversionRate, formConversionRate, mqlRate | totalOpps, totalTriggered, oppsAmount, triggeredAmount | cpMql, cpOppInfluenced, cpOppTriggered | channel, goal, adFormat, audienceSize, statusLabel | previewUrl CONVO/MESSAGE AD CAVEAT: when adFormat is CONVO or MESSAGE (LinkedIn message ads), success is measured by opens, sends, and actionClicks (and costPerOpen / costPerSend), NOT clicks/ctr/cpc. Do not rank these ads by CTR or dismiss them when clicks=0. Use sort='actionClicks,desc' or sort='opens,desc' for conversational performance ranking. RULES: Field 'id' corresponds to endpoint queried. Exclude $0 CPL experiments from calculations.
    ConnectorAPI key
  • Replace a form draft’s logic document with the given calculations — the ONLY valid logic structure; any other shape is stored but silently ignored by the engine and invisible in the builder. A calculation runs on every change of the submission: when every `conditions[].expression` is true, the `then` effects apply; otherwise the `otherwise` effects. Expression syntax (identical for field formulas): field references MUST be wrapped in backticks and text values quoted — `amount` > 1000, `region` = "west" AND `age` >= 18. Bare identifiers are rejected. Functions: MAX, MIN, ROUND, ABS, FLOOR, CEIL, and for multi-value/composite fields CONTAINS(`group`, "option") (membership; substring on text; any cell of a table's rows), CONTAINS(`table`, "column", "value") (membership in one column), COUNT(`group`) (items or table rows), SUM(`table`, "column") or SUM(`list`), PART(`address`, "city") (absent parts are ""), ISBLANK(`field`) (true while the field has no answer; the one function tolerant of a missing reference — use it for is-empty/is-filled conditions, with = FALSE for filled). No others. Effect operators: VARIABLE {target, expression} computes into a field slug; SHOW/HIDE {fields: [slugs]} for rule-driven visibility (the static field property `visible` is separate); FUNCTION {target, function e.g. FORMAT_TO_CURRENCY, fields: [source slug]}; SET_OUTCOME {target, message?, severity?}; SET_WORKFLOW_STATE {target}; SEND {notification, documents?, emails?}; REFERENCE_NUMBER {target, generator: sequence slug}; SEND_TO_ZAPIER {connection: slug of a connection the organization configured under Settings → Integrations — NOT a URL, and you cannot create connections; queued only when a submission actually saves, never on previews}; COLLECT_PAYMENT {payment: {amountExpression: formula for the total, currency?, description?, recipients: [{account: payment-account slug from Settings → Payments, percent? XOR amountExpression?}]} — at most ONE per form; amounts are always priced server-side and the customer pays before the submission lands}; DELIVER_OBJECT {objects: [numeric ids from list_objects]} — hands the submitter the named library files through a per-submission download link (and a {{download_link}} merge value in notification templates); when the form also collects a payment the files unlock only after it succeeds, automatically. SEND.emails entries may be literal addresses or the recipient descriptors assignee|owner|creator|field:<slug> — field: is how an anonymous submitter’s own address is reached. Slugs come from get_form_fields; read get_form_logic first because this replaces the whole document. To change or delete individual calculations on a form that already has logic, prefer patch_form_logic — it applies a diff and cannot drop the calculations you did not mention. Requires form:write.
    Connector
    Destructive
    API key
  • Save a form’s draft. Per-document semantics, verified against the service: a document you pass (`schema`, `settings`) replaces THAT document wholesale; documents you omit are untouched — read the current one first or you will erase what exists. Logic and workflow are NOT written here — use update_form_logic and update_form_workflow, which validate their structures. For individual field properties, prefer patch_form_fields. Saving a draft does not affect the live form until publish_form. Requires form:write.
    Connector
    Destructive
    API key
  • Use when the user asks "which flights between X and Y have Starlink?" or "what Starlink flights serve airport X?". Single-route lookup: returns United Airlines flight numbers on a route (or touching an airport) ranked by Starlink probability. Pass both origin+destination for a specific route, OR just one to list all Starlink flights from/into an airport. For trip planning with connections, use plan_starlink_itinerary instead — this tool has no connection logic or coverage-ratio ranking. Empty result = route not served by Starlink planes.
    ConnectorNo auth
  • Actually ask the audience. THIS SPENDS THE WORKSPACE'S CREDITS and cannot be undone. Returns `run_id`, `study_id` and `web_url`; the result arrives through get_study(run_id). Credits are debited as the study executes, and the estimate is claimed against the workspace's daily agent budget at submission. Call estimate_study first unless the study is small, and ask the user before submitting anything with confirm_recommended=true. Poll get_study every 5 to 10 seconds, and no faster than once per 10 seconds per study when several are in flight: the key allows 30 calls a minute in total. kind: pick by what respondents are shown, and pass ONLY that kind's material; another kind's field is refused (kind_mismatch) rather than ignored. closed_question a question with 2-8 answer options (add 'Not sure' if they are not exhaustive) open_question answered in their own words, coded into themes preference_test choose between 2-12 written options, with reasons (the web app's creative test for copy or concepts) image_reaction react to 1-3 images (the web app's creative test for pictures). Respondents see the pixels, so pass the image itself, never your description of it: host attachments as image_files first; else request_upload, send the file, then image_refs; a public address as image_urls. Never invent a download_url or file_id. A rough sketch of an IDEA may instead be described in words in an open_question or preference_test with material_is_description=true. url_feedback a page test: first impression, three ratings, then your question survey / guide a questionnaire (survey) or interview guide (guide): pass instrument_id from the web app's library, or transcribe the user's document into `questions` in order and tell them skip logic, grids and pictures do not carry over focus_group a moderated discussion over `topics`, 3 to 8 seats audience_ids: from list_audiences. respondents: per audience; the default is 50, or the kind's smaller size (url_feedback 30, focus_group 8). Ask for more only when the user wants more, and stay inside what today's workspace budget still covers. respondents_by_audience overrides per id. study_id: an earlier study's id, to ask the SAME respondents a follow-up (the whole panel answers again with their earlier answers in front of them; there is no per-option targeting). notes: the research goal, verbatim, for the report.
    Connector
    Destructive
    OAuth