stablebaseline.io

Search available tools by keyword or category.

List supported diagram types.

Get DSL writing instructions for a diagram type.

SOFTWARE & CLOUD architecture icons ONLY (AWS, Azure, GCP, Docker, Kubernetes, databases, message queues, dev tools, etc.).

Semantic search over the 276 AntV Infographic templates — call this FIRST when building an `infographic` diagram so you pick the right structure for the content.

Get the CDMD markdown language specification.

Return the calling user's identity (user_id, display_name, full_name, email, avatar_url).

Server-side searchable, paginated list of USERS and TEAMS that can be assigned as the owner of an improvement/task in a project — and the canonical source for resolving a person's user_id when @-mentioning them in a document.

List teams in an organization, with optional search filter and an `includeMembers` flag that fans out to v_team_members in a single round-trip.

Get a single team by ID with profile-enriched member list (display_name, email, avatar_url, role, joined_at).

List organisations you have access to.

List workspaces you have access to.

List projects in a workspace.

List folders in a project.

Create a folder in a project.

Update a folder (rename/move/reorder).

Delete a folder recursively, including all nested folders and documents.

Batch-reorder folders within a parent (or project root) by setting sibling positions.

List AND grep documents in a project, workspace, or folder.

Get the complete folder and document tree for a project in one call.

Get the folder and document tree.

Read a document's content with line numbers.

Create a document from CDMD markdown (standard Markdown plus SB extensions — call getCdmdLanguageGuide if unfamiliar).

Edit a document: the PREFERRED tool for small targeted changes.

Find and replace EXACT substrings in a document (NOT regex: wildcards and patterns are matched literally).

Get a diagram's full details including raw DSL source code.

Insert a new diagram into a document.

Update a diagram's code, description, or properties.

Delete a diagram: removes the database record AND every reference to it in the document body — the current marker format plus legacy forms (markers without an embedded diagramId, and old plain-text `[Diagram: name]` placeholders).

Delete a document.

Get the Stable Baseline whiteboarding guide (Markdown): when to use stencils vs architecture icons vs code/BPMN diagrams vs plain shapes vs real images vs frames/presentations, how to lay out and verify a board, and how to edit a large board safely (patch by id, never replace).

Auto-design a complete, visually polished whiteboard from a natural-language goal using the PREMIUM multi-agent pipeline (the same one the in-app assistant uses): it browses the stencil/icon library, composes the WHOLE board, renders it, critiques the rendered image, and refines — far better than hand-placing shapes.

Design ONE reusable, on-brand SLIDE COMPONENT and add it to the org's component library so every future branded deck (autoDesignWhiteboard designProfile:'branded-executive') can use it.

Mask-edit (inpaint) one region of an image element on a whiteboard.

Create or refine a slide deck INSIDE an existing whiteboard by conversing with the AI design agent.

Create or refine a standalone ILLUSTRATION INSIDE an existing whiteboard by conversing with the AI design agent.

Get the design agent's reply after calling designDeckInWhiteboard OR designIllustrationInWhiteboard: the status (thinking/building/ready) and EITHER the finished result (a deck's slide count + preview, or the placed illustration) OR a clarifying question to answer (call the SAME tool you started with, passing the sessionId + your answer).

Export a design that lives in a whiteboard to an editable PowerPoint (PPTX), a PDF, or PNG images.

Invite the Stable Baseline Meeting Scribe bot to a LIVE meeting (Zoom, Google Meet, Microsoft Teams, or Webex) so it paints a live, editable whiteboard of the conversation as it happens: sticky notes and topic clusters, an agenda that ticks itself off, and decisions and actions pinned to rails, on a real board the team keeps working in afterwards.

Get a meeting scribe's status after startMeetingScribe: the session state (joining, in the waiting room, live in the call, paused, ending, ended, or failed), the live activity feed of what the scribe has painted, and the board it is painting.

Stop a running meeting scribe: the bot leaves the meeting and the board is finalised (tidy pass plus a summary frame).

Create a whiteboard — an infinite Excalidraw canvas.

List AND grep the whiteboards in a project (hidden whiteboard-kind documents).

Read a whiteboard: its metadata plus a summary of the canvas (element count, element types, and text labels on the board).

Edit elements on a whiteboard's canvas WITHOUT dropping the rest of the scene.

Author shapes onto a whiteboard from high-level specs (you do NOT need the full Excalidraw element schema).

Copy-paste existing whiteboard elements — the MCP equivalent of selecting a group and pressing Ctrl/Cmd+D.

Insert a real IMAGE (photo, screenshot, logo, picture) into a whiteboard — the storage-backed equivalent of insertImageInDocument.

Insert (or re-render in place) a real DIAGRAM (BPMN, Diagrams-as-Code / any DSL: mermaid, d2, plantuml, graphviz, …) on a whiteboard as an editable SB diagram element.

Turn a raster image into hand-drawn freedraw strokes on a whiteboard, deterministically.

Render tabular data as an aligned grid of labelled cells on a whiteboard, deterministically.

Search the built-in library of structural whiteboard stencils — ready-made hand-drawn graphics: flowchart/UML/ER/BPMN symbols, scrum columns, org-chart nodes, gantt, lo-fi/UX wireframe widgets (buttons, forms, tables, alerts, navs), charts, device frames, stick figures.

Render a whiteboard to a raster IMAGE so you can SEE it and confirm your edits look right, then iterate — like taking a screenshot.

Delete a whiteboard (the host document and its canvas).

Generate a diagram from its DSL/code and get the IMAGE back — WITHOUT inserting it into any document or whiteboard.

Render a diagram that ALREADY exists in a document to an IMAGE (svg/png/jpeg @1x/2x/3x) and return it — a temporary imageUrl available for 1 hour plus, for png/jpeg, the image inline so you can see it, and title/url citing the document the diagram lives in.

Internal maintenance (requires write).

MOVE documents between folders and/or reorder them — the batch filing tool.

List version history for a document.

Get image details including a fresh signed URL (expires after 1 hour).

Create a PUT upload URL for a document image (max 10MB).

Insert an image into a document (max 10MB).

Update image metadata (alt, caption, nlDescription, dimensions, alignment) — metadata only; to change the picture itself, delete it and insert the new one.

Delete an image: removes the stored file, the database record, AND the image from the document body — both the IMAGE marker in the markdown and the image node in the document's rich-text content, so the picture stops appearing on every read.

Create a PUT upload URL for a Vega/Vega-Lite data file.

Delete a data file attachment from a document.

Step 1 of file ingest.

Step 2 of file ingest.

Read the current status of an ingest job.

List AND grep improvements in a project.

Get full details for an improvement item including evidence, activity log, compliance context, and the `checklist` array (each item: id, text, due_date, completed_at, plus server-stamped attribution).

Create an improvement item in a project.

Update an improvement (or a task — tasks share this row, but prefer the symmetric updateTask alias when working from getTask).

Delete an improvement and all associated evidence and activity.

List improvement categories for a project.

Create an improvement category or sub-category.

Update an improvement category.

Delete an improvement category.

Reorder improvement categories by setting sort_order values.

Add evidence to an improvement.

Add a comment or activity entry to an improvement.

Update a comment on an improvement.

Delete a comment from an improvement.

Ranked semantic search over IMPROVEMENTS AND TASKS — hybrid full-text + vector, so it matches meaning rather than just wording.

List AND grep plans in a project.

Get full plan details including phases, items, and activity.

Create a plan in a project.

Update a plan.

Delete a plan, all its phases, and all tasks/improvements within it.

List phases for a plan ordered by position.

Get a plan phase by ID with full details.

Create a phase in a plan.

Update a plan phase.

Delete a plan phase and all tasks/improvements within it.

Reorder plan phases by setting position values.

Add a comment or activity entry to a plan.

Update a comment on a plan.

Delete a comment from a plan.

Create a task in a plan.

List AND grep tasks in a plan.

Get a task by ID with full details, evidence, activity, and the `checklist` array (each item: id, text, due_date, completed_at, plus server-stamped attribution).

Update a task.

Get the complete plan hierarchy (phases, tasks, improvements) in one call.

Set or clear the WBS parent-child nesting of a task/improvement (outline hierarchy, no scheduling effect).

List FS/SS/FF task-dependency edges in a plan (the Gantt arrows).

Create an FS/SS/FF scheduling edge with lag/lead between two items in the same plan (rendered as a Gantt arrow).

Change the type (FS/SS/FF) or lag/lead of an existing task-dependency.

Remove a task-dependency edge.

Per-item: apply a successor's `suggested_start_date`/`suggested_end_date` to its real dates and clear `needs_dependency_review`.

Per-item: clear `needs_dependency_review` without changing dates — keeps the edge, ignores the suggestion.

Auto-schedule every item in a plan so all FS/SS/FF task-dependencies are respected (topological pass, durations preserved).

Dry-run of `applyTaskDependencyCascade` — returns the diff without writing.

Unified Knowledge Graph KNOWLEDGE retrieval — facts, themes and relationships from INSIDE document CONTENT.

Phase 5 / E3 — Provenance-aware assessor for a set of chunk_ids returned by kg_search.

Fetch a KG entity by id or name, with 1-hop neighbours.

Find other sources that share entities with the given source.

Check whether Knowledge Graph is in-scope for a given target.

Linked-mentions rail: every edge whose dst matches the named entity.

List Louvain communities for an org (optionally scoped by project).

Fetch a community wiki page (LLM-curated CDMD).

3 template + 3 LLM-generated sample questions for the knowledge-graph playground.

Read a single organisation by id.

Read a single workspace by id.

Read a single project by id.

List members of an organisation, enriched with email + display name.

Fetch a single organisation member by user_id, enriched with profile (email + display name).

List organisation invitations.

Read the subscription state for an organisation.

List invoices for an organisation, newest first.

List saved payment methods for an organisation.

Composite credit balance for an organisation: plan_credits (recurring monthly bucket), top_up_credits (purchased one-offs, gross), bonus_credits (admin grants), total, and period_end (next plan reset).

List active credit packages available for purchase (name, credits, bonus_credits, price in cents AUD).

List credit-purchase history for an organisation, newest first.

Read the public catalog entry for a single subscription tier (free, pro, enterprise).

List explicit permission grants on a resource (workspace/project/folder/document/improvement/plan), including principal type (user|team), level (none|read|write|admin), and 3-state overrides for documents/improvements/plans.

Compute a user's effective permission level on a resource (taking team grants, inheritance, and 3-state overrides into account) and the source.

List every kg_scope row for the caller's organisation, optionally narrowed to a workspace or project subtree.

Read an organisation's settings JSON and the derived enabled-features map (plans, documents, improvements, compliance, knowledge_graph — all booleans).

Read the plan entitlements (limits + capability flags) that apply to the caller's organisation.

Read the calling user's preferences.

Create a new organisation owned by the calling credential's user.

Update an organisation's name and/or description.

Create a new workspace inside the organisation.

Update a workspace's name.

Create a new project inside a workspace.

Update a project's name, description, and/or icon.

Invite a person by email to the credential's organisation.

Cancel a pending invitation by id.

Resend a pending invitation: extends expires_at by 7 days and re-triggers the invitation email.

Update an organisation member's role (admin or member).

Soft-deactivate or reactivate an organisation member.

Hard-remove a member from an organisation, cascading to workspace and team memberships and resource permissions.

Update a user's profile name and/or display email.

Add an existing organisation member to a workspace with a workspace-level role.

Change an existing workspace member's role.

Remove a member from a workspace.

Create a new team inside an organisation.

Update a team's name, description, and/or colour.

Delete a team.

Add a user to a team as a regular member.

Remove a user from a team.

Grant a team read/write/admin access to a workspace.

Update an existing team's workspace access level.

Revoke a team's workspace access.

Insert or update a resource_permissions row for a user OR team on a workspace/project/folder/document/improvement/plan.

Update the access level on an existing permission row.

Delete a resource_permissions row.

Set a single 3-state override on a permission row: null=inherit, true=allow, false=deny.

Preview a subscription tier or seat change.

Apply a previously previewed subscription change.

Preview the consequences of cancelling.

Apply a previewed soft cancellation (cancel_at_period_end=true).

Quote a credit-package purchase (first half of the human-in-the-loop ritual).

Apply a credit-package quote by creating a hosted Stripe Checkout session.

Reactivate a subscription that was scheduled to cancel at period end (clears cancel_at_period_end).

Update the org's billing email.

Mint a single-use Stripe Customer Portal URL for self-serve billing changes.

Toggle whether a workspace is in the Knowledge Graph (on/off/inherit).

Set the KG visibility mode for a project: 'strict' (multi-source rows hidden unless user can read every source), 'permissive' (one source suffices), or 'open' (any org member).

Toggle KG-scope override for a folder (on/off/inherit).

Toggle KG-scope override for a single document (on/off/inherit).

Cancel a single KG rebuild batch.

Emergency stop for KG ingestion: cancels queued/running build runs, queued/running rebuild batches, demotes still-eager unfinished chunks.

Wipe + re-ingest a single document in the KG.

Preview the credit cost, source counts, and ETA of including or excluding KG scope rows.

Apply a previously previewed KG scope change.

Preview the cost / coverage / ETA of a full KG rebuild for the org (optionally narrowed to a workspace or project).

Apply a previously previewed KG rebuild.

Update an organisation's `settings` JSONB via deep merge.

Create a per-org BRAND KIT so Stable Baseline outputs come out fully on-brand.

List an organisation's BRAND KITS (palette/fonts/logo), newest first.

Set or clear the default BRAND KIT at a scope: organization, workspace, project, folder, or document.

Toggle organisation feature modules (plans, improvements, compliance, knowledge_graph, documents, meeting_scribe).

Update the calling user's preferences.

Begin an agent-driven sign-up to Stable Baseline.

Poll the status of a signup begun via `startSignup`.