Plotline

List all Plotline products (apps) the authenticated user has access to. Returns each product's ID and name. Call this tool FIRST before any other tool — you need a product ID for all other operations. Returns: { products: [{ id, name, capabilities? }] }. On /v2/mcp only workspaces with MCP enabled are listed, and `capabilities` names what propose_changes can change there (for example push, in-app, widgets, stories, gamification, surveys).

list_products

Analyze activity and performance for one authorized product using read-only SQL. First read plotline://skills/analytics and relevant schemas using get_plotline_knowledge; search_plotline_knowledge finds metric definitions and joins. Supports joins, CTEs, subqueries and aggregations. Use {name:Type} parameters for values. Queries are automatically restricted to the selected product. Results include columns, rows and queryId; requests exceeding limits return an error without partial results.

Finish an upload started with request_upload: checks the file arrived, adds it to the product's asset library and returns the asset with its `url`. Call it only after the HTTP PUT to uploadUrl succeeded, with the same productId, type and key. If no file is found at the key, or the file is over the size limit, nothing is added: fix the problem and start again with request_upload. Unlike propose_changes, the asset is added straight away, so call it only for a file the user asked you to add.

Optional. Generates 1 to 3 images and hosts them on Plotline, returning {images: [{url, aspectRatio}]}. If your client can generate images itself, you may use that instead: upload the result with request_upload and complete_upload, never to another host. Give a `brief` (what the image is for, e.g. a Diwali sale banner for a bottom sheet) or an exact `imagePrompt`. Read the workspace's brand guidelines with search_plotline_knowledge first and put the relevant colours and style in the brief. Pick `aspectRatio` from where the image goes (see plotline://knowledge/recipes/images). `referenceAssetId` (an IMAGE in this product's asset library) is used as a style or content reference. The images are not added to the asset library unless `saveToLibrary` is true; only set it when the user asks to keep them. The returned url can be used straight away in a propose_changes draft (an IMAGE node's value or a bgImage). Show the images to the user before using them.

Check a proposal made with propose_changes: status (PROPOSED, APPLIED, REJECTED, STALE, EXPIRED, SUPERSEDED), the reviewer's comment, and why it went stale. A STALE proposal means the data changed after it was proposed: read the documents again and propose again. Also returns a fresh previewUrl (valid 10 minutes) to look at the proposal in a browser.

Read a complete Plotline knowledge document or schema by registered ID or plotline:// URI. Start with plotline://guide or search_plotline_knowledge. Returns content and versions, equivalent to native resources/read. Use the registered IDs or plotline:// URIs returned by search. Also reads a workspace's own knowledge document by the plotline://workspace/... URI that search_plotline_knowledge returned in workspaceResults.

Propose edits for a person to review and approve in the Plotline dashboard. NOTHING is changed until someone approves it there. Supported today: AI Director objectives (decisioningObjectives): create, edit setup (Strategy brief = `statement`, Guardrails = `strategy`, goal events, audience, holdout/rollout), delete, and add/rename/move/remove topics and subtopics; and a subtopic's SMS, email or push copy (aiDirectorContent): add, edit or remove variants, or create the content for a subtopic that has none. Push variants have title, body and optional Android subtitle (plain text; image and deeplink are kept; a new push variant may copyFromSlot to reuse a sibling's image and deeplink). Email variants have subject, preheader and the text of the layout's blocks (read them with read_object on aiDirectorContent); addBlocks adds a block copied from an existing one; a new email variant needs copyFromSlot or templateId. New copy is saved as Draft unless the reviewer also approves it for sending; approved email is re-rendered after approval. And AI Director signals (decisioningSignals): create, edit (name, question, answer type, options, audience, evaluation windows, attribute key, default value, schedule) and delete; publishing and pausing stay in the dashboard. And SQL segments (cohorts): create, edit (name, description, sqlDefinition.query, sqlDefinition.description) and delete a segment whose members are a ClickHouse SELECT returning UserRefID. Test the SQL with analytics_query first and write sqlDefinition.description in plain words; read plotline://knowledge/recipes/sql-segment. Filter segments made in the dashboard can't be changed here. And standalone mobile push campaigns (outsideAppCampaigns, type PUSH): create a draft from a template, edit content (including the rich layout: text, images, buttons and links, carousels, countdown timers; read plotline://knowledge/recipes/push-layout), audience, trigger, schedule, frequency and goals, and delete; live campaigns keep their audience, trigger and schedule (goals stay editable); publishing, pausing and sending stay in the dashboard (read plotline://knowledge/recipes/push-campaign first). And standalone email campaigns (outsideAppCampaigns, type EMAIL): create a draft (sender, subject, preview text, subscription topic, a template's body via templateId), edit any of those and the body, a BeeFree page started from a template or written from scratch (read plotline://knowledge/recipes/email-body; there is no HTML input), audience, trigger, schedule, frequency and goals, and delete; live emails keep their body, audience, trigger and schedule; publishing, test sends and sending stay in the dashboard (read plotline://knowledge/recipes/email-campaign first). And standalone SMS campaigns (outsideAppCampaigns, type SMS): create a draft, edit the provider (an smsProviders _id) and message text (checked for length in SMS parts), audience, trigger, schedule, frequency and goals, and delete (read plotline://knowledge/recipes/sms-campaign first). And standalone web push campaigns (outsideAppCampaigns, type WEB_PUSH): create a draft, edit title, body, https click link, icon, image, up to 2 buttons and ttl, audience, trigger, schedule, frequency and goals, and delete (read plotline://knowledge/recipes/web-push-campaign first). And standalone RCS campaigns (outsideAppCampaigns, type RCS): create a draft from an rcsTemplates templateId or from scratch (messageType text, image, video, card or carousel, with content, suggestions and options, including an SMS fallback), edit the provider (an rcsProviders _id), audience, trigger, schedule, frequency and goals, and delete (read plotline://knowledge/recipes/rcs-campaign first). Live SMS, web push and RCS keep their audience, trigger, schedule and goals; publishing, test sends and sending stay in the dashboard. And in-app campaigns and widgets (flows + steps): insert each step (stepType MODAL, BOTTOMSHEET, TOOLTIP, SPOTLIGHT, FULLPAGECONTENT, FULLPAGEMODAL, PIPVIDEO, FLOATER, BANNER, or WIDGET for a widget; a layout tree of containers, text, buttons, images, video, Lottie, carousels, grids and custom HTML, or a templateId; placement on a pages screen and element; triggerEvents) with a ref and the flow that lists it (steps: ["$ref:<ref>"], isWidget true for a widget) in the same proposal; edit a step's layout, placement, trigger and behaviour; add, remove or reorder steps through the flow's steps; edit the flow's audience, schedule, frequency and goals; and delete. Live campaigns can be edited (it reports LIVE_EDIT and needs publish permission). Publishing, pausing, test users, real-time filters and A/B tests stay in the dashboard (read plotline://knowledge/recipes/inapp-campaign or plotline://knowledge/recipes/widget, and plotline://knowledge/recipes/inapp-layout, first). And stories (stories + slides): insert each slide (slideType IMAGE, VIDEO or LOTTIE with an https backgroundUrl, optional overlay layout) with a ref and the story that lists it (slides: ["$ref:<ref>"]), placed on a story strip element (page + clientElementId); edit, reorder or remove slides through the story; edit the story's label, thumbnail, audience, schedule and goals; and delete (read plotline://knowledge/recipes/story first). And surveys (studies): create a survey with its questions (TEXT, MCQ_SINGLE_CHOICE, MCQ_MULTIPLE_CHOICE, SCALE_NPS, SMILEY_RATING, PROMPT), answer rules and thank-you screen, edit them, the trigger events, audience, schedule, response limits and goals, and delete (read plotline://knowledge/recipes/survey first). And gamification (needs the gamification capability): rewards and coupons (rewards; read plotline://knowledge/recipes/reward); luck games, a flows document with isGamification true and a game object holding the template, theme, trigger, reward slots with probabilities and copy, for scratch card, spin the wheel, slot machine, gift or card reveal, video reveal and direct reward (read plotline://knowledge/recipes/luck-game); quizzes and skill games (studies; read plotline://knowledge/recipes/quiz); streaks and milestones (flows with campaignType STREAK or MILESTONE; read plotline://knowledge/recipes/streak or plotline://knowledge/recipes/milestone); and the rewards page (rewardsPage; read plotline://knowledge/recipes/rewards-page). A game gives only ACTIVE rewards, so propose the rewards first when they do not exist. Publishing and pausing stay in the dashboard. And journeys (journeys): create a draft journey graph (ENTRY, waits, conditions, action branches, splits, attribute, segment and track-event nodes, EXIT) whose message nodes are in-app overlay steps or push, email, SMS, web push or RCS campaigns inserted in the same proposal, each node's _id being its child's ref; edit nodes, edges, entry trigger, audience, schedule, re-entry and goals; edit a message's content through its step or campaign; remove a node (its child is deleted); delete a draft or stopped journey. WhatsApp, webhook, voice, widget and game nodes, publishing and test users stay in the dashboard (read plotline://knowledge/recipes/journey first). Before the first call, read plotline://knowledge/recipes/propose-changes with get_plotline_knowledge; read current documents with read_object so patches target real ids. Send one user intent per proposal (many changes are fine). Use dryRun:true to check without saving. Returns {status, changeSetId?, reviewUrl?, previewUrl?, previewExpiresAt?, summary, issues[]}: status INVALID means nothing was saved; fix each error (it has path and hint) and call again. previewUrl (saved proposals and dry runs) is a read-only page, valid 10 minutes, showing only the rendered preview (add ?view=both for before/after): if you have a browser, open it, wait for [data-preview-ready="true"], check the result, and show the user a screenshot. If you can view the preview, you MUST do so before telling the user the proposal is ready: compare it with what the user asked for (content, layout, images, buttons, each step) and, if it does not match, fix the proposal and call again with supersedes instead of handing it over. Always share previewUrl with the user as a link (valid 10 minutes). When saved, also share the reviewUrl and say it is waiting for their approval. To revise a pending proposal, pass supersedes=<changeSetId>.

Read product objects: event definitions, attributes, campaigns (flows: in-app campaigns and widgets), their steps (steps: pass parentId, the flowId or journeyId), campaign themes (themes), captured app screens with their elements and widget placeholders (pages: project elements only for the screen you need), step templates (stepTemplates: Plotline's plus the product's saved ones; project out layout when listing), stories, their slides (slides: pass parentId, the storyId), surveys with their questions embedded (studies), rewards (rewards), the workspace's rewards page (rewardsPage: one item, its _id is the product id; no filter or projection), journeys (nodes embedded; a message node's step or outsideAppCampaigns document has the node's _id), AI Director objectives (decisioningObjectives: topics/subtopics are embedded in intentSets), AI Director signals (decisioningSignals: a question the model answers per user, saved to a signal_* user attribute), rendered email bodies (emailContentDocuments), email layouts (emailTemplates: Plotline's built-ins, which have no productId, plus the product's own; project {title:1,source:1}; content is large) and their groups (emailTemplateGroups), email subscription topics (subscriptionTopics), email providers and verified senders (emailSenders: no credentials; only sender, status and tracking fields), SMS providers (smsProviders: no credentials; only name, provider type and status), RCS templates (rcsTemplates: Plotline's, shared by every product) and RCS providers (rcsProviders: no credentials; name, provider type, status and whether the SMS fallback is set up), segments (cohorts: project {name:1,status:1,source:1}; SQL segments have definitionType SQL and sqlDefinition.query/description), Android notification channels (androidNotificationChannels), push templates (pushNotificationTemplates: Plotline's built-ins, which have no productId, plus the product's own; project out expandedLayout) and their groups (pushNotificationTemplateGroups), the workspace's saved skills (skills: playbooks the team wrote for recurring tasks; list them with projection {slug:1,title:1,description:1} before starting a task and read the instructions of any that applies; see plotline://schema/objects/skills) and aiDirectorContent: a subtopic's copy as the flat view propose_changes edits (SMS text; push title and body; email subject, preheader and layout blocks as plain text; filter on stored fields such as parentCampaignId, type, aiDirector.intentId; no projection). For in-app campaigns, first read plotline://knowledge/recipes/inapp-campaign; for widgets, plotline://knowledge/recipes/widget; for stories, plotline://knowledge/recipes/story; for surveys, plotline://knowledge/recipes/survey; for journeys, plotline://knowledge/recipes/journey. For push campaigns, first read plotline://knowledge/recipes/push-campaign; for email campaigns, plotline://knowledge/recipes/email-campaign; for SMS campaigns, plotline://knowledge/recipes/sms-campaign (providers: smsProviders, no credentials); for web push campaigns, plotline://knowledge/recipes/web-push-campaign; for RCS campaigns, plotline://knowledge/recipes/rcs-campaign. For AI Director, first read plotline://knowledge/recipes/ai-director-objective (signals: plotline://knowledge/recipes/ai-director-signal). Fetch one with filter {_id: {$oid: id}}, limit 1, or list using filters, projection, sorting and pagination. Read plotline://skills/object-read and plotline://schema/objects/<collection> through get_plotline_knowledge for fields and filter examples. Access is automatically restricted to the selected product. Returns {collection,items,hasMore,nextSkip?} using Extended JSON for typed values. Read-only; no aggregation pipelines or cross-collection joins.

Start adding one image, video or Lottie file to the product's asset library. Returns {uploadUrl, key, uploadHeaders, expiresInSeconds, maxFileSizeBytes}. Send the file with an HTTP PUT to uploadUrl using exactly uploadHeaders, before expiresInSeconds runs out, then call complete_upload with the same key. Nothing is added to the library until complete_upload succeeds; an upload that is never completed is discarded. Use it only for a file the user asked you to add, and never send the user's file to any other host. Allowed: IMAGE (png, jpg, jpeg, gif, webp; SVG is not accepted) up to 1.0 MB, VIDEO (mp4) up to 50.0 MB, LOTTIE (json, lottie) up to 1.0 MB. If the file is larger, ask the user to compress it.

Search Plotline's analytics reference: table and object schemas, metrics, relationships and SQL examples. Returns IDs, resource URIs, snippets and versions; fetch relevant documents with get_plotline_knowledge or resources/read. These references describe how to read and interpret data; they contain no customer records. Pass productId to also search that workspace's own knowledge: brand guidelines, policies, product facts and other documents the team saved in the dashboard. Those come back in workspaceResults, each with a plotline://workspace/... URI for get_plotline_knowledge. Search it before writing any copy or content for a workspace, and follow what it says about brand and policy.