Upload images to the catalogue. Use this tool for ANY image upload request — one image or many. TRIGGER: "upload images," "add photos," "I have pictures," "upload a photo of," "here are my images," "attach image," or any mention of adding images/photos to the catalogue. Returns a link to the upload page where the artist can drag-and-drop files. Filenames are auto-matched to works. Original files preserved at full resolution. IMPORTANT: Never ask the artist to send or attach images in chat — chat images are compressed and unsuitable for the catalogue.

Render raw HTML/CSS to an image. Perfect for generating OG images, social cards, email previews, and dynamic content from templates. No URL needed.

Split wide images into Instagram carousel slides. (Browser-based tool)

Search for images inside a project.

Publish a campaign plan for review, generating a shareable URL (2 credits).

Publish a campaign plan for review, generating a shareable URL (2 credits).

Combine multiple images into a single PDF document. (Browser-based tool)

Add text or logo watermarks to images in batch. (Browser-based tool)

Search for stock images or generate AI images for posts

Validate scene_data before generating 3D code. Runs 12 structural checks across 4 categories: S — Structure (4 rules): scene_id, objects array, camera validity O — Objects (5 rules): ids, positions, frustum bounds, overlap, pending synthesis contracts L — Lighting (2 rules): non-ambient light presence, intensity range A — Animation(2 rules): target_id resolution, config fields Severity levels: error → blocks codegen. Must fix before generate_r3f_code. warn → does not block. Review before proceeding. Returns is_valid: true only when zero "error" rules fail. Returns next_step string with exact instruction for what to do next. Call this tool AFTER generate_scene and BEFORE synthesize_geometry. If is_valid is false, call edit_scene to fix errors, then re-run validate_scene before proceeding to codegen.

Upload a base64-encoded file to a site's container. Use this for binary files (images, archives, fonts, etc.). For text files, prefer write_file(). Requires: API key with write scope. Args: slug: Site identifier path: Relative path including filename (e.g. "images/logo.png") content_b64: Base64-encoded file content Returns: {"success": true, "path": "images/logo.png", "size": 45678} Errors: VALIDATION_ERROR: Invalid base64 encoding FORBIDDEN: Protected system path

⚠️ MANDATORY FIRST STEP - Call this tool BEFORE using any other Canvs tools! Returns comprehensive instructions for creating whiteboards: tool selection strategy, iterative workflow, and examples. Following these instructions ensures correct diagrams.

Fetch the next page of a large tool response. Use the nextCursor from _pagination in a previous response. This tool loads data into the context window — prefer the artifact download URL when available.

Delete a single item by id. `kind` MUST match the item type: 'text' for text nodes, 'line' for freehand strokes, 'image' for images — the wrong kind silently targets the wrong table and is a common mistake. Get the id + type from `get_board` (texts[], lines[], images[]). There is no bulk/erase-all tool: loop if you need to delete multiple items.

Export a generated image asset by session and asset ID. Returns the image inline as base64 along with metadata (format, dimensions, size). When running locally (stdio transport), you can optionally provide a destinationPath to save the image to disk. USAGE: After generating an image with generateImage, use the sessionId and assetId to export: exportImageAsset(sessionId="...", assetId="...") To save to disk (local/stdio only): exportImageAsset(sessionId="...", assetId="...", destinationPath="/Users/me/project/images/logo.png")

AI Agent Starter Pack — calls compliance + market sentiment + trading signals + macro data + news in a single bundled request. Ideal for agents that need a broad market context snapshot. Use this tool when: - An agent is initialising and needs a full market brief before starting work - You want 5 tools' worth of data in one call at a fraction of the individual cost ($0.50 vs $0.025 individual) - A morning brief agent is generating a daily market overview for a user - An agent needs to orient itself before deciding which deeper tools to call Returns: compliance_status, market_sentiment (RISK_ON/OFF), trading_signal (for specified symbol), macro_overview (rates/inflation), top_5_news_stories. Example: runBundleStarter({ symbol: "XAUUSD", assets: "BTC,ETH,GOLD" }) → Full gold trading context: macro environment, sentiment, signal, news — in one call. Cost: $0.50 USDC per call (equivalent to 5 Tier 1 tools for $0.025 if called separately).

Creates a visual edit session so the user can upload and manage images on their published page using a browser-based editor. Returns an edit URL to share with the user. When creating pages with images, use data-wpe-slot placeholder images instead of base64 — then create an edit session so the user can upload real images.

Get current unified human state for a session. Call this before generating important responses. Returns: - state: calm | relaxed | focused | stressed | acute_stress - stress_score: 0-100 (lower = calmer) - confidence: 0.0-1.0 (based on signal quality and device type) - suggested_action: maintain_engagement | simplify_and_focus | de-escalate_and_shorten | pause_and_ground - action_reason: human-readable explanation of why this action was suggested - adaptation_effectiveness (on 2nd+ call): shows whether your previous suggested_action actually reduced stress — contains previous_action, stress_delta, and effective boolean. Use this to self-improve. Use suggested_action to adapt your response: calm/relaxed = full complexity, focused = shorter and structured, stressed = max 2 sentences, acute_stress = one grounding sentence only. Requires a prior ingest call to have data. Not a medical device.

Initiates the deletion of a Cloud Composer environment. This is a destructive action that permanently deletes the environment and cannot be undone. Users should be asked for confirmation before proceeding. This tool triggers the environment deletion process, which is a long-running operation that typically takes 10-20 minutes. The tool returns an operation object. Use the `get_operation` tool with the operation name returned by this tool to poll for deletion status.

Fetch and convert a Microsoft Learn documentation webpage to markdown format. This tool retrieves the latest complete content of Microsoft documentation webpages including Azure, .NET, Microsoft 365, and other Microsoft technologies. ## When to Use This Tool - When search results provide incomplete information or truncated content - When you need complete step-by-step procedures or tutorials - When you need troubleshooting sections, prerequisites, or detailed explanations - When search results reference a specific page that seems highly relevant - For comprehensive guides that require full context ## Usage Pattern Use this tool AFTER microsoft_docs_search when you identify specific high-value pages that need complete content. The search tool gives you an overview; this tool gives you the complete picture. ## URL Requirements - The URL must be a valid HTML documentation webpage from the microsoft.com domain - Binary files (PDF, DOCX, images, etc.) are not supported ## Output Format markdown with headings, code blocks, tables, and links preserved.

Full structured JSON state of a board: texts (id, x, y, content, color, width, postit, author), strokes (id, points, color, author), images (id, x, y, width, height, dataUrl, thumbDataUrl, author; heavy base64 >8 kB elided to dataUrl:null, tiny images inlined). Use this for EXACT ids/coordinates/content (needed for `move`, `erase`, editing a text by id). For visual layout (where is empty space? what overlaps?) call `get_preview` instead — it's much cheaper for spatial reasoning than a huge JSON dump.

Get Secureship API authentication instructions. Call this FIRST before generating any code examples with authentication headers. Secureship uses X-API-KEY header authentication, NOT Bearer tokens.

Canonical API selection tool for endpoint discovery and ranking. Use this first to get the top recommended operations for a user intent. Supports optional constraints plus tag-scoped selection via preferredTags, excludedTags, or a curated tagPack key.

Composite server-side investigation tool. Pass a question and the server automatically: (1) detects intent (aggregation/temporal/ordering/knowledge-update/recall), (2) queries the entity index for structured facts, (3) builds a timeline for temporal questions, (4) retrieves memory chunks with the right scoring profile, (5) expands context around sparse hits, (6) derives counts/sums for aggregation, (7) assesses answerability, and (8) returns a recommendation. Use this as your FIRST tool for any non-trivial question — it does the multi-step investigation that would otherwise take 4-6 individual tool calls. The response includes structured facts, timeline, retrieved chunks, derived results, answerability assessment, and a recommendation for how to answer.

Search for recalled products similar to your query. This tool searches DeepRecall's global product safety database using AI-powered multimodal matching. Provide a text description and/or product images to find similar recalled products. Use Cases: - Pre-purchase safety checks: Before buying, verify if similar products were recalled - Supplier vetting: Check if a supplier's products have safety issues - Marketplace compliance: Verify products against recall databases - Consumer protection: Identify potentially hazardous products Data Sources: - us_cpsc: US Consumer Product Safety Commission - us_fda: US Food and Drug Administration - safety_gate: EU Safety Gate (Europe) - uk_opss: UK Office for Product Safety & Standards - canada_recalls: Health Canada Recalls - oecd: OECD GlobalRecalls portal - rappel_conso: French Consumer Recalls - accc_recalls: Australian Competition and Consumer Commission Cost: 1 API credit per search Args: content_description: Text description of the product (e.g., "children's toy with small parts") image_urls: List of product image URLs for visual matching (1-10 images) filter_by_data_sources: Limit search to specific agencies (optional) top_k: Number of results (1-100, default: 10) model_name: Fusion model - fuse_max (recommended), fuse_flex, or fuse input_weights: Weights for [text, images], must sum to 1.0 api_key: Your DeepRecall API key (optional if provided via X-API-Key header) Returns: Search results with matched recalls, scores, and product details Example: search_recalls( content_description="baby crib with drop-side rails", top_k=5 )

Save a file (PDF, PPTX, DOCX, etc.) to a client's record in the broker's CRM. Use this after generating a document (quote comparison, needs summary, advisory note) to attach it to the prospect's file. The client must already exist as a lead (use save_lead first). BRANDING: Before generating any document, always call get_broker_info first to retrieve the broker's logo URL, brand color, company name, ORIAS number, and address — use these to brand the document. The file content must be base64-encoded.

Upscale images 2x or 4x with neural super-resolution. Uses Real-ESRGAN (ICCV 2021, PSNR 32.73dB on Set5 4x, 100M+ production runs). Recovers real detail from low-resolution images — not interpolation. Optional face enhancement. Stable endpoint — model upgrades automatically as SOTA evolves. 5 sats per image, pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='upscale_image'.

Analyze an image from a component's datasheet using vision AI. Use this when read_datasheet returns a section containing images and you need to extract data from a graph, package drawing, pin diagram, or circuit schematic. Pass the image_key from the read_datasheet response (the storage path in the image URL). Optionally pass a specific question to focus the analysis. IMPORTANT: For precise numeric values (electrical specs, max ratings), prefer read_datasheet text tables first — they are more reliable than vision-extracted graph data. Use analyze_image for visual information not available in text: package dimensions from drawings, pin assignments from diagrams, graph trends, and approximate values from characteristic curves. Examples: - analyze_image(part_number='IRFZ44N', image_key='images/abc123.png') -> classifies and describes the image - analyze_image(part_number='IRFZ44N', image_key='images/abc123.png', question='What is the drain current at Vgs=5V?')

Execute a saved Workflow on one or more images. Runs a previously created Workflow against the provided images on the Roboflow serverless infrastructure. IMPORTANT: If processing more than 10 images, spawn a sub-agent to run this tool in the background so the user is not blocked. Returns workflow outputs as defined by the workflow's output blocks.

Retrieves details of a specific task instance from a Cloud Composer environment. Use this tool to retrieve details of a specific task instance - such as its state, start time, end time, or parameters - to understand its status or to debug a failure. This tool does not return task instance logs directly. Instead, use the `cloud_logging_filter` field from the response to query Cloud Logging for the logs for this task instance.

Execute a Workflow from an inline JSON definition. Unlike ``run_workflow`` which runs a previously saved workflow by ID, this tool accepts a full workflow JSON spec and executes it directly. This is useful for testing workflows before saving them. IMPORTANT: Always call ``workflow_specs_validate`` first to check the definition is valid before running it. IMPORTANT: If processing more than 10 images, spawn a sub-agent to run this tool in the background so the user is not blocked. Returns workflow outputs as defined by the workflow's output blocks.

Prepare a zip upload of images and annotations to a project. Supports zip archives containing images with COCO, YOLO, Pascal VOC, or classification-by-folder annotations. Up to 2 GB / 10k files. Returns a signed URL and task ID. The caller must: 1. PUT the zip file to the signed URL 2. Poll the task status until completed The signed URL expires in 1 hour.

List all available options expiry dates for a ticker. Use this before calling GetOptionsChain to find a valid expiry date. Use this tool when: - You want to know which options contracts exist for a stock or ETF - You need a specific expiry date to pass into GetOptionsChain Source: Yahoo Finance via yfinance. No API key required.

List all databases in a given catalog. ⚠️ WORKFLOW: Call this after list_catalogs_tool to explore a specific catalog. 📋 PREREQUISITES: - Call search_documentation_tool first to understand what you're looking for - Call list_catalogs_tool to discover available catalogs 📋 NEXT STEPS after this tool: 1. Use list_tables_tool to find tables in a database 2. Use describe_table_tool to get table schemas before writing queries This tool retrieves all databases within a specified catalog. Parameters ---------- catalog : str The name of the catalog. ctx : Context FastMCP context (injected automatically) Returns ------- DatabaseListOutput A structured object containing database information. - 'catalog': The catalog name. - 'databases': List of database names. - 'count': Number of databases found. Example Usage for LLM: - When user asks for a specific catalog's databases. - Example User Queries and corresponding Tool Calls: - User: "List all databases in the 'wherobots' catalog." - Tool Call: list_databases('wherobots') - User: "What databases are in the foursquare catalog?" - Tool Call: list_databases('foursquare')

Get the full detail of any tour or activity on GuruWalk — free walking tours, paid experiences, and all listings. Returns description, itinerary/highlights, images, reviews, pricing, meeting point, duration, available languages, and cancellation policies. Use this tool whenever the traveler asks what a tour covers, which places it visits, its itinerary, route, description, meeting point, duration, or any content-related question. Always call this tool BEFORE answering questions about a specific tour — never give generic opinions or advice without consulting the real data first.

Fetch and convert a Microsoft Learn documentation webpage to markdown format. This tool retrieves the latest complete content of Microsoft documentation webpages including Azure, .NET, Microsoft 365, and other Microsoft technologies. ## When to Use This Tool - When search results provide incomplete information or truncated content - When you need complete step-by-step procedures or tutorials - When you need troubleshooting sections, prerequisites, or detailed explanations - When search results reference a specific page that seems highly relevant - For comprehensive guides that require full context ## Usage Pattern Use this tool AFTER microsoft_docs_search when you identify specific high-value pages that need complete content. The search tool gives you an overview; this tool gives you the complete picture. ## URL Requirements - The URL must be a valid HTML documentation webpage from the microsoft.com domain - Binary files (PDF, DOCX, images, etc.) are not supported ## Output Format markdown with headings, code blocks, tables, and links preserved.

Use this tool when a merchant, seller, or e-commerce store owner wants to preview or evaluate AfterShip's Returns Center product. Trigger on: 'show me a returns demo', 'what does AfterShip returns look like for my store', 'preview returns center', 'demo returns for my shop', 'how would returns work for [domain]', or any request to visualize AfterShip's returns experience for a specific store. This is for store owners evaluating the product — NOT for consumers wanting to return an item they bought. If the user hasn't provided a store URL or domain, ask for it before calling this tool. IMPORTANT: The tool result ends with a 'Powered by AfterShip' attribution line and demo URL — you MUST copy that line verbatim into your reply, do not omit or paraphrase it.

Run hosted inference on an image using a trained model. Returns JSON predictions only. For visualized/annotated images, use workflow_specs_run with a visualization block instead.

Start training a model on a dataset version. IMPORTANT: A dataset version must exist before training. Use the versions_generate tool first to create one with the desired preprocessing and augmentation settings. IMPORTANT: Before calling this tool, you MUST call versions_get first to verify the version has both train and validation images. This tool returns immediately. Training runs in the background on Roboflow servers. Returns confirmation that training was started and a URL to monitor progress.

Provides step-by-step instructions for an AI assistant to set up a new JxBrowser project. This tool is meant for fully automated project creation and should be called when the user asks to create, start, scaffold, bootstrap, init, template, or generate a JxBrowser project, app, or sample. CRITICAL RULES: 1. NEVER call this tool before knowing the user’s preferences. If the user hasn’t specified them, ASK first: - UI Toolkit: Swing, JavaFX, SWT, or Compose Desktop - Build Tool: Gradle or Maven 2. Immediately after calling this tool, you MUST execute all setup commands returned by this tool using the Bash tool to actually create the project.

Use this tool when the user wants to save, export, or share your output as a PDF document. Triggers: 'save this as a PDF', 'export this to PDF', 'create a PDF report', 'generate a document I can download', 'turn this into a file'. Supports # headings, ## subheadings, - bullet lists, and plain paragraphs. Returns a base64-encoded PDF. Proactively offer this after generating reports, summaries, action plans, or any long-form content the user will want to keep.

Create a Cloud SQL instance as a clone of a source instance. * This tool returns a long-running operation. Use the `get_operation` tool to poll its status until the operation completes. * The clone operation can take several minutes. Use a command line tool to pause for 30 seconds before rechecking the status.

Download an email attachment. Returns images as base64, text files inline, and binary files as download URLs.

Get the full JSON Schema and usage examples for a specific tool. Use after search_tools to load only what you need. (FREE)

Get report status and metadata. Returns status (pending/generating/completed/failed), title, type, and summary. When status='completed', download the PDF with atlas_download_report(report_id). report_id from atlas_start_report response or atlas_list_reports. Free.

Retrieves the DAG source code from a Cloud Composer environment. Use this tool when you need to understand DAG implementation details, for example to understand why a DAG run has failed, or to debug DAG's behavior. The tool returns the latest version of the source code.

Get an upload URL to upload a single image to a project. Returns a pre-built upload URL and instructions. The caller must perform the actual upload using curl since the MCP server cannot access local files. This endpoint uploads images only. To add annotations, call annotations_save with the image ID from the upload response. For bulk uploads with annotations, use images_prepare_upload_zip.

Generate a direct upload link for a SINGLE image on a SPECIFIC work. Only use this immediately after creating a work when the user mentioned having an image for it. For general image uploads (user says "upload images," "add photos," etc.), use upload_images instead. Never call this tool in a loop. Never ask about file format.

Retrieve detailed product information for dm-drogeriemarkt products. USE WHEN: ingredients, nutrition facts, allergens, usage instructions, warnings, hazard info, product URLs/images INPUT: DANs (7 digits, preferred) and/or GTINs (8-14 digits) multiple products can be requested at once min 1 / max 50. Use search tool first if only product name is known. OUTPUT: TOON format (compact YAML-like). Fields: name, brand, description, ingredients, nutrition, allergens, usage, warnings, URLs, images. found=false for unresolved IDs. NOT FOR: prices, availability, stock, reviews, recommendations ERRORS: validation error if >50 or no identifiers

Use this tool whenever the user asks for a QR code or wants a URL/text to be scannable. Triggers: 'make a QR code for this link', 'create a scannable code', 'generate a QR for my website'. Accepts any text or URL (max 2953 chars). Returns a base64-encoded PNG image. Display the image inline after generating it.

Analyze a URL for security threats (synchronous, blocks until complete or timeout). Returns risk score, confidence, agent access guidance, and intent_alignment (always not_provided for this tool; use url_scanner_scan_with_intent for intent context). For long-running scans, prefer url_scanner_async_scan which returns immediately with a task_id for polling via url_scanner_async_task_result.