# Jigsawstack — how to use (mcp.ai)

Connect your Jigsawstack account and use 23 tools for artificial intelligence straight from your AI agent. Connect with your own API key. JigsawStack provides a suite of custom small AI models integrated into scalable infrastructure, enabling developers to build AI-powered applications efficiently.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_jigsawstack?ms=1787293680000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `jigsawstack_check_nsfw`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/jigsawstack`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/jigsawstack/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/jigsawstack/check/nsfw` — Tool to detect NSFW content in images. Use when you need to quickly detect nudity, violence, hentai, porn and other NSFW content in images.
  - body: { url?: string, file_store_key?: string }
- `POST https://api.mcp.ai/api/jigsawstack/check/profanity` — Tool to check text for profanity and inappropriate language. Use when you need to validate user-generated content, filter inappropriate language, or sanitize text input.
  - body: { text: string, censor_replacement?: string }
- `POST https://api.mcp.ai/api/jigsawstack/check/spam` — Tool to perform spam check analysis on text. Use when you need to detect spam content and get a spam confidence score.
  - body: { text: string }
- `POST https://api.mcp.ai/api/jigsawstack/check/spelling` — Tool to check and correct spelling errors in text. Use when you need to validate text for spelling mistakes and get correction suggestions.
  - body: { text: string, language_code?: string }
- `POST https://api.mcp.ai/api/jigsawstack/classify/content` — Tool to classify text and image datasets using custom labels. Use when you need to categorize content into predefined labels.
  - body: { labels: object[], dataset: object[], multiple_labels?: boolean }
- `POST https://api.mcp.ai/api/jigsawstack/convert/html/to/any` — Tool to convert HTML to images (PNG/JPEG/WEBP) or PDF, or capture website screenshots. Use when you need to generate visual representations of HTML content or web pages.
  - body: { url?: string, html?: string, type?: string, width?: integer, height?: integer, quality?: integer, full_page?: boolean, return_type?: string }
- `POST https://api.mcp.ai/api/jigsawstack/create/embedding/v2` — Tool to generate enhanced vector embeddings with speaker fingerprint support using the v2 model. Use when you need to create embeddings from text, images, audio, or PDF files.
  - body: { url?: string, text?: string, type: string, query?: boolean, dimensions?: integer, instruction?: string, file_store_key?: string, speaker_fingerprint?: boolean, token_overflow_mode?: string }
- `POST https://api.mcp.ai/api/jigsawstack/create/prediction` — Tool to forecast time series data using AI-powered prediction. Use when you need to predict future values based on historical data patterns.
  - body: { steps?: integer, dataset: object[] }
- `POST https://api.mcp.ai/api/jigsawstack/create/prompt` — Tool to create a new prompt in the Prompt Engine for reusable LLM interactions. Use when you need to store and manage prompt templates with variable inputs.
  - body: { inputs?: object[], prompt: string, prompt_guard?: string[], return_prompt?: string|object[]|object }
- `POST https://api.mcp.ai/api/jigsawstack/create/voice/clone` — Tool to create a cloned voice for text-to-speech synthesis. Use when you need to clone a voice from an audio sample for later use in TTS operations.
  - body: { url?: string, name: string, file_store_key?: string }
- `POST https://api.mcp.ai/api/jigsawstack/detect/objects` — Tool to recognize and identify objects within an image using computer vision AI. Use when you need to detect and locate objects in images.
  - body: { url?: string, file_store_key?: string }
- `POST https://api.mcp.ai/api/jigsawstack/extract/vocr` — Tool to recognize, describe and retrieve data within images with great accuracy using Vision OCR. Use when you need to extract text, data fields, or descriptions from images or PDFs.
  - body: { url?: string, prompt?: string|string[]|object, page_range?: integer[], fine_grained?: boolean, file_store_key?: string }
- `POST https://api.mcp.ai/api/jigsawstack/get/search/suggestions` — Tool to get real-time search suggestions for a given query. Use when you need to provide autocomplete suggestions or related search queries.
  - body: { query: string }
- `POST https://api.mcp.ai/api/jigsawstack/get/sentiment` — Tool to retrieve sentiment analysis via GET request. Use when you need to classify text into positive, negative, or neutral sentiment using a GET endpoint.
  - body: { text: string }
- `POST https://api.mcp.ai/api/jigsawstack/image/generation` — Tool to generate images from text prompts. Use when you need visual content created from a prompt.
  - body: { url?: string, steps?: integer, width?: integer, height?: integer, prompt: string, return_type?: string, aspect_ratio?: string, output_format?: string, advance_config?: object, file_store_key?: string }
- `POST https://api.mcp.ai/api/jigsawstack/list/prompts` — Tool to list all prompts stored in the Prompt Engine. Use when you need to retrieve or view stored prompts.
  - body: { page?: integer, limit?: integer }
- `POST https://api.mcp.ai/api/jigsawstack/run/prompt/by/id` — Tool to execute a stored prompt using its prompt engine ID. Use when you need to run a pre-configured prompt template with dynamic input values.
  - body: { id: string, stream?: boolean, input_values?: object }
- `POST https://api.mcp.ai/api/jigsawstack/scrape/website` — Tool to scrape any website and extract structured data using AI-powered element prompts or CSS selectors. Use when you need to extract specific information from web pages without writing custom scrapi
  - body: { url?: string, html?: string, scale?: integer, width?: integer, height?: integer, scroll?: boolean, cookies?: object[], features?: string[], wait_for?: object, byo_proxy?: object, is_mobile?: boolean, selectors?: string[], size_preset?: string, goto_options?: object, http_headers?: object, page_position?: integer, advance_config?: object, element_prompts?: string[]|object, force_rotate_proxy?: boolean, root_element_selector?: string, reject_request_pattern?: string[] }
- `POST https://api.mcp.ai/api/jigsawstack/sentiment/analysis` — Tool to analyze text sentiment. Use when you need to classify text into positive, negative, or neutral sentiment.
  - body: { text: string }
- `POST https://api.mcp.ai/api/jigsawstack/summarize/text` — Tool to generate concise, intelligent summaries of text or documents with AI. Use when you need to condense long content into bullet points or paragraphs.
  - body: { url?: string, text?: string, type?: string }
- `POST https://api.mcp.ai/api/jigsawstack/text/to/speech` — Tool to convert text to natural-sounding speech. Use when you need to generate an audio file from text input.
  - body: { text: string, accent?: string, speaker_clone_url?: string, speaker_clone_file_store_key?: string }
- `POST https://api.mcp.ai/api/jigsawstack/translate/text` — Tool to translate text from one language to another. Use when you need to convert text between different languages with automatic language detection support.
  - body: { text: string|string[], target_language: string, current_language?: string }
- `POST https://api.mcp.ai/api/jigsawstack/web/search` — Tool to perform AI-powered web search with AI overview and geo-aware results. Use when you need concise search results enriched with AI summary and location context.
  - body: { query: string, byo_urls?: string[], ai_overview?: boolean, auto_scrape?: boolean, max_results?: integer, safe_search?: string, spell_check?: boolean, country_code?: string }

## Example prompts
- "What can I do in Jigsawstack?"
- "Show me a summary of my Jigsawstack account"

## More
- Page: https://mcp.ai/jigsawstack
- Agent spec (llms.txt): https://mcp.ai/jigsawstack/llms.txt
- Postman collection: https://mcp.ai/jigsawstack/postman.json