Jigsawstack MCP integration
Reads text out of customer attachments, translates and voices replies, and screens submitted text and images before they reach the queue.
23actions available
Three actions you can hand over today
Every action runs live through MCP. Nothing to build, nothing to maintain.
Detect objects in image
Lyro analyzes customer images to identify products, issues, or anomalies. Your team diagnoses visual problems instantly without asking for more details.
Summarize text
Lyro condenses long support tickets into key points for faster triage. Your team handles more cases per day by reading summaries instead of full walls of text.
Web search
Lyro searches the internet for current information to answer customer questions. Your team provides up-to-date solutions without waiting for internal research.
How businesses use Jigsawstack + Lyro
Each card is one request a support team gets, and the Jigsawstack actions Lyro runs to close it.
Read the receipt a customer just uploaded
Lyro runs vision OCR over an attached image or PDF, identifies what is in it, and condenses a long document to the few lines that answer the question, so nobody retypes an order number by hand.
Extract Data with Vision OCRDetect Objects in ImageSummarize TextAnswer in the customer's language, in audio if they need it
Lyro detects the incoming language, translates the reply, checks it for spelling errors, and can return it as natural speech for customers who would rather listen than read.
Translate TextCheck SpellingText to SpeechScreen user-submitted content before it is published
Lyro scores an incoming message for spam and profanity and checks any attached image for NSFW content, so a review, comment, or support attachment is flagged before a human ever opens it.
Check SpamCheck ProfanityCheck Image for NSFW ContentRun the prompt templates your team maintains
Lyro stores an approved prompt in the Prompt Engine, lists what already exists so nobody duplicates it, and runs one by ID with the customer's details filled in as variables.
Create PromptList PromptsRun Prompt By ID
How it works
Get started in 3 steps
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Jigsawstack actions it has and picks the ones a request needs.
Connect Jigsawstack
Authorize the Jigsawstack account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Jigsawstack actions that close it and chains as many as the request needs.
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free
Jigsawstack · Lyro
What can you do in Jigsawstack without me setting anything up?
These, right away:
- Create embedding v2
- Check image for nsfw content
- Check profanity
Great, let's start with the first one.
FAQ
Everything else about Jigsawstack
Setup, permissions, and the limits of what Lyro can do inside Jigsawstack.
Yes. Web Search returns AI-summarised, geo-aware results, Get Search Suggestions surfaces related queries, and Scrape Website extracts structured data from a specific page using element prompts or CSS selectors. That covers questions your help center has no article for, such as a courier's current status page.
Every action available in Jigsawstack
All 23 actions your agent can call on Jigsawstack, straight from the live MCP connection.
Check image for nsfw content
Detect NSFW content in images.
Check profanity
Check text for profanity and inappropriate language.
Check spam
Perform spam check analysis on text.
Check spelling
Check and correct spelling errors in text.
Classify content
Classify text and image datasets using custom labels.
Convert HTML to image or PDF
Convert HTML to images (PNG/JPEG/WEBP) or PDF, or capture website screenshots.
Create embedding v2
Generate enhanced vector embeddings with speaker fingerprint support using the v2 model.
Create prediction
Forecast time series data using AI-powered prediction.
Create prompt
Create a new prompt in the Prompt Engine for reusable LLM interactions.
Create voice clone
Create a cloned voice for text-to-speech synthesis.
Detect objects in image
Recognize and identify objects within an image using computer vision AI.
Extract data with vision ocr
Recognize, describe and retrieve data within images with great accuracy using Vision OCR.
Get search suggestions
Get real-time search suggestions for a given query.
Get sentiment
Retrieve sentiment analysis via GET request.
Generate image from prompt
Generate images from text prompts.
List prompts
List all prompts stored in the Prompt Engine.
Run prompt by ID
Execute a stored prompt using its prompt engine ID.
Scrape website
Scrape any website and extract structured data using AI-powered element prompts or CSS selectors.
Sentiment analysis
Analyze text sentiment.
Summarize text
Generate concise, intelligent summaries of text or documents with AI.
Text to speech
Convert text to natural-sounding speech.
Translate text
Translate text from one language to another.
Web search
Perform AI-powered web search with AI overview and geo-aware results.
The tools Jigsawstack sits next to
Same connection, same setup. Pick the next one your team already uses.
Botpress
Attributes workspace usage to individual bots, provisions workspaces and integrations, updates workflows, and drives runtime conversations.
Elevenreader
Reports voices and character usage, builds conversational agents with indexed knowledge bases, tunes pronunciation, and queues outbound batch calls.
Kaggle
Searches datasets, models, and competitions, publishes and versions datasets, pulls notebook code and output, and files competition entries.
Openai
Reports on running batch and fine-tuning jobs, maintains and searches vector stores, transcribes or voices audio, and runs moderation and evals.
Semanticscholar
Finds papers by title, topic, or text snippet, traces citations and references, and profiles authors with their publication metrics.
Wit.ai
Parses messages into intents, entities and traits, detects language, adds training data, and audits or exports an app's model.
Ready to connect Jigsawstack?
Authorize the account and your agent has all 23 actions from the first conversation.