Classifies incoming text into taxonomy categories, extracts named entities with confidence scores, and maintains the classifiers behind both.
6actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro runs a full content analysis covering entities, intent, and meaning in a single call. Your team gets complete context on customer inquiries without running separate extraction tools.
Ayro pulls out names, locations, organizations, and other key entities from customer messages automatically. Your team instantly spots the important details buried in customer text.
Ayro sorts customer inquiries into predefined categories in real-time for smart routing. Your team routes tickets to the right department without manual triage.
Each card is one request a support team gets, and the Textrazor actions Ayro runs to close it.
Ayro classifies the text against a built-in taxonomy such as IAB Content Taxonomy 3.0 or IPTC Media Topics and reads back the categories with their confidence scores, so routing follows the subject rather than a keyword.
Ayro extracts the people, places, and companies mentioned, each with a type, confidence score, and relevance score, and applies thresholds to both so only the meaningful entities reach the answer.
Ayro creates and updates custom classification categories and maintains entity dictionaries of domain terms, so later analysis recognises product names and internal language the built-in taxonomies miss.
Ayro reads the account's subscription plan, concurrent request limit, and daily usage, so a long classification run is measured against the remaining allowance before it starts.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Textrazor actions it has and picks the ones a request needs.
Authorize the Textrazor account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Textrazor actions that close it and chains as many as the request needs.
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 freeTextrazor · Ayro
What can you do in Textrazor without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Textrazor.
Classify Text ships with built-in classifiers including textrazor_iab for IAB QAG segments, textrazor_iab_content_taxonomy_3.0 from 2022, and textrazor_mediatopics_2023Q1 for IPTC Media Topics, plus other versions of those taxonomies. Ayro can also target a custom classifier you built through Manage Custom Classifiers.
All 6 actions your agent can call on Textrazor, straight from the live MCP connection.
This tool retrieves comprehensive information about a TextRazor account, providing essential details about the account's status, usage, and limits.
This tool will classify text into predefined categories using TextRazor's classification capabilities.
This tool manages custom classifiers in TextRazor, allowing users to create, update, and manage custom classification categories.
Manage custom entity dictionaries in TextRazor for enhanced named entity recognition.
Extract named entities (people, places, companies, etc.) from text using TextRazor's entity extraction API.
A comprehensive content analysis tool that combines multiple TextRazor extractors to perform a complete analysis of the input text.
Same connection, same setup. Pick the next one your team already uses.
Attributes workspace usage to individual bots, provisions workspaces and integrations, updates workflows, and drives runtime conversations.
Registers a GitHub repository for analysis and answers plain-language questions about its architecture, functionality, and dependencies.
Searches datasets, models, and competitions, publishes and versions datasets, pulls notebook code and output, and files competition entries.
Reports on running batch and fine-tuning jobs, maintains and searches vector stores, transcribes or voices audio, and runs moderation and evals.
Finds papers by title, topic, or text snippet, traces citations and references, and profiles authors with their publication metrics.
Queries a knowledge graph for grounded answers, uploads and indexes new documents into it, and unlinks the files that have gone out of date.

Authorize the account and your agent has all 6 actions from the first conversation.
