Wit.ai

Wit.ai MCP integration

Parses messages into intents, entities and traits, detects language, adds training data, and audits or exports an app's model.

Connect Wit.aiSee all integrations

31actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

  • Wit.AI get message

    Lyro analyzes customer text to extract intents, entities, and traits in one call. Your team understands exactly what customers are asking for without manual parsing.

  • Create wit.AI app

    Lyro creates a new Wit.ai app to train custom language understanding models. Your team builds domain-specific NLU without leaving the conversation.

  • Add entity keyword

    Lyro adds keywords and synonyms to Wit.ai entities to improve intent detection. Your team teaches Lyro to recognize your industry terminology automatically.

See all 31 actions

How businesses use Wit.ai + Lyro

Each card is one request a support team gets, and the Wit.ai actions Lyro runs to close it.

  • Get the structured meaning out of a message

    Lyro sends the text through the app's model to extract its intent, entities, and traits, and detects which locale it was written in with confidence scores before deciding how to route it.

    Wit.ai Get MessageWit.ai Detect LanguageGet Intent Details

  • Teach the model something it does not know yet

    Lyro defines a new intent, adds the custom entity type it depends on, and submits annotated training utterances so the gap a customer just exposed is covered in the next parse.

    Create Wit.ai IntentCreate Wit.ai EntityCreate Wit.ai Training Utterances

  • Widen the vocabulary an entity recognises

    Lyro adds a keyword to a keywords entity, attaches the synonyms customers actually type for it, and extends a trait with an extra value when the existing ones are too coarse.

    Add Entity KeywordAdd Keyword SynonymAdd Value to Trait

  • Audit and back up what the app has learned

    Lyro reviews the training utterances filtered by intent, lists the app's tag groups to see which snapshots exist, and exports the whole app as a backup ZIP with a download URL.

    List UtterancesList App TagsExport App Data

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 Wit.ai actions it has and picks the ones a request needs.

  1. 01

    Connect Wit.ai

    Authorize the Wit.ai 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.

  2. 02

    Tell your agent what you need

    Describe the job the way you would hand it to a teammate. Lyro maps it to the Wit.ai actions that close it and chains as many as the request needs.

  3. 03

    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
Wit.ai · Lyro

Everything else about Wit.ai

Setup, permissions, and the limits of what Lyro can do inside Wit.ai.

  • Create Wit.ai Training Utterances is rate limited to 200 samples per minute. For a large import Lyro paces the calls against that ceiling rather than submitting everything at once, and List Utterances confirms afterwards what actually landed.

Every action available in Wit.ai

All 31 actions your agent can call on Wit.ai, straight from the live MCP connection.

  • Add entity keyword

    Add a keyword with optional synonyms to a Wit.ai entity.

  • Add keyword synonym

    Add a new synonym to a keyword in an entity.

  • Add value to trait

    Add a new value to an existing trait in Wit.ai.

  • Create wit.AI app

    Create a new app in Wit.ai.

  • Create wit.AI entity

    Create a new entity in Wit.ai.

  • Create wit.AI intent

    Create a new intent in Wit.ai.

  • Create wit.AI trait

    Create a new trait in Wit.ai.

  • Create wit.AI training utterances

    Add training utterances (samples with annotations) to your Wit.ai app.

  • Delete app

    Delete a specific app from wit.ai.

  • Delete entity

    Permanently delete an entity by name.

  • Delete entity keyword

    Delete a keyword from a keywords entity in wit.ai.

  • Delete entity role

    Delete a specific role from an entity in wit.ai.

  • Delete intent

    Permanently delete an intent by name.

  • Delete keyword synonym

    Delete a synonym from a keyword in an entity.

  • Delete utterances

    Delete validated utterances (training samples) from your Wit.ai app.

  • Wit.AI detect language

    Detect the language of a given text input.

  • Export app data

    Export Wit.ai app data as a backup ZIP file.

  • Get app details

    Retrieve metadata and settings of a Wit.ai app.

  • Get entity details

    Retrieve details of a specific entity including keywords and roles.

  • Get intent details

    Retrieve details of a specific intent.

  • Get intents

    List all intents in a Wit.ai app.

  • Wit.AI get message

    Analyze a text message and extract its intent, entities, and traits.

  • Get trait details

    Retrieve details of a specific trait.

  • List traits

    List all traits in a Wit.ai app.

  • Get voice details

    Retrieve details for a specific text-to-speech voice.

  • List wit.AI apps

    Retrieve the list of all Wit.ai apps for the authenticated user.

  • List app tags

    Retrieve all tag groups (versions) for a Wit.ai app.

  • List entities

    List all entities in a Wit.ai app.

  • List utterances

    Retrieve training utterances (samples) from a Wit.ai app.

  • List voices

    Retrieve all available text-to-speech voices grouped by locale.

The tools Wit.ai sits next to

Same connection, same setup. Pick the next one your team already uses.

Browse every integration

Ready to connect Wit.ai?

Authorize the account and your agent has all 31 actions from the first conversation.

Connect Wit.aiTalk to sales
Support agent working at a laptop next to the Lyro mascot