The MCP tool directory.

Insert a new column in an existing table.

Insert a new row in an existing table.

Insert text at a specific position in the document. Use index 1 to insert at the beginning of the body.

Merge cells in a table. Specify the top-left cell and span.

Find and replace all occurrences of text in the entire document.

Unmerge previously merged cells in a table.

Update paragraph style (alignment, spacing, indentation, heading) for a range.

Update text style (bold, italic, font, color, etc.) for a range of text. Only specified fields are changed.

Expensive LLM job — does not spend a researched cluster. Generates an AI content brief for a content idea using web research. The brief specifies outline, key points, tone, CTAs — everything a writer needs. Stores the result in the idea's Brief field for review before content generation.

Expensive LLM job — writing from a researched workstream does not spend a second cluster. Triggers content generation for an approved content idea. Enqueues a job that runs research, writing, and editorial review. Creates a ContentItem with the generated markdown when done.

Expensive LLM job — writing from a researched workstream does not spend a second cluster. Enqueues a content generation job for a ContentItem with a Brief. The job runs the full writer pipeline: research, two-call writer split, section-targeted expansion, editorial review with glossary/structural-marker enforcement, and post-editor glossary repair. The item's Content is overwritten UNCONDITIONALLY when the job completes — there is no skip-guard on the existing Content, so calling this on an already-populated item regenerates from the Brief. Description and MetaDescription are also overwritten. Returns immediately with the job ID; poll get_content_generation_status(jobId) for phase/progress/last-alive, or poll get_content_item for the finished article — UpdatedAt advances at every phase transition so you can distinguish 'in progress' from 'silently failed'. Item must have a Brief; the Brief should specify the desired length, or set 'targetWordCount' on the item via update_content_item.

Expensive LLM job — does not spend a researched cluster. Generates an AI image for a brand. Two models are available: 'gemini-3.1-flash-image-preview' (Nano Banana 2 — fast, default) and 'gpt-image-2' (GPT Image 2.0 — higher quality). If 'model' or 'aspectRatio' is omitted, the brand's defaults from upsert_visual_style (defaultModel / defaultAspectRatio) are used as fallbacks before the built-in default. The 'prompt' can be plain text OR a JSON object encoded as a string. When using JSON, keys are merged with the brand's visual style — per-image keys take precedence over brand defaults. Use get_visual_style to see what's already configured. Recognized JSON keys (first-class — influence the rendering): 'imageDescription' (the main subject — required if no plain-text prompt), 'altText', 'style', 'colorScheme' / 'colorPalette', 'mood', 'motif', 'lighting', 'composition', 'additionalInstructions', 'constraints' (array of negative prompts). Translatable keys (carried through localization): 'imageDescription', 'altText', 'text', 'title', 'caption', 'description'. Unknown keys pass through verbatim to the image model — useful for one-off experiments, but the brand-level fields above are what flow consistently across calls. Note: 'aspect' is NOT a recognized JSON key — pass aspect ratio via the 'aspectRatio' parameter, not in the JSON body. Example JSON prompt: {"imageDescription":"Cute robots working in a garden","motif":"isolated subjects","lighting":"soft natural daylight"}. Returns the public URL of the generated image.

Generate an AI image from a text prompt using Claude Imagine credits. Returns the image URL.

$0.50 USDC: generate deterministic vLLM or llama.cpp launch templates from an exact StackBench recommendation without claiming a launch occurred.

Generate a complete project kit with optimal tech stack and MCP recommendations based on project description.

Generate dialect-correct ALTER TABLE migration SQL + rollback from a plain-English intent. Output uses the connection's exact dialect (ALTER TABLE for all three, plus pg-specific `USING` casts / mssql-specific `sp_rename` / mysql-specific `MODIFY COLUMN`). Never executes. Check response `dialect` field before manually editing — don't hand-translate across dialects. [BUILD tier]

Generate a PlantUML diagram with automatic syntax validation and error reporting for auto-fix workflows. Returns embeddable image URLs for valid diagrams or structured error details for invalid syntax that can be automatically corrected. Optionally saves the diagram to a local file.

Generate realistic, schema-aware INSERT statements for development and testing. Respects types, constraints, and FK relationships. Never executes. [BUILD tier]

Generates TypeScript types for a project.

Get detailed information about a specific voice archetype including tweet examples

Get detailed information about a specific copywriting framework for a network

Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.

Get all available categories for a specific social media network

Truncate text to fit within the 'before fold' character limits for each social media platform for previewing purposes

Fetch trending social media content from the HyperFeed API

Extract the three-dimensional learning components (SEP: Science and Engineering Practices, DCI: Disciplinary Core Ideas, CCC: Crosscutting Concepts) for a specific standard (e.g., MS-PS1-1, MS-LS2-3, MS-ESS3-1)

Get information about the ATS Resume Writer: how to obtain an access code (pay-what-you-want, $0 works), what the rewrite engine does, and the companion resume kit. Call this when rewrite_resume reports a missing or invalid access code.

Call this FIRST on every build — the plan, usage, limits and FEATURES MATRIX (forms, data, bookings, chatbot, media) and how much of each is left; design only within it. Also lists unassigned leftovers to reuse before creating new ones.

Overview of the account: reachable mailboxes/domains, plan tier, and the monthly send quotas (used / remaining / limit). monthlySends is the API/MCP quota that send_message draws from; campaigns are metered separately under campaignSends. Useful before large sends.

Overview of the account: reachable mailboxes/domains, plan tier, and the monthly send quotas (used / remaining / limit). monthlySends is the API/MCP quota that send_message draws from; campaigns are metered separately under campaignSends. Useful before large sends.