Witai MCP server

Connect Witai to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

Deploy WitaiBook a demo

What you can do with the Witai MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the list apps tool in Witai
  • Use the list utterances tool in Witai
  • Use the export app tool in Witai
  • Use the delete app tag tool in Witai
  • Use the create intent tool in Witai
  • Use the update app tool in Witai

Supported Tools

list_apps

List Apps

List all Wit.ai apps accessible by the current token. Returns app metadata including name, language, and training status. Supports pagination.

list_utterances

List Utterances

List training utterances (samples) in the Wit.ai app. Returns annotated utterances with their intent, entity, and trait labels. Supports pagination.

export_app

Export App

Export the current Wit.ai app configuration as a downloadable ZIP file containing its intents, entities, traits, utterances, and settings.

delete_app_tag

Delete App Tag

Delete a version tag from a Wit.ai app. Call list_apps to discover accessible app IDs. This cannot be undone.

create_intent

Create Intent

Create a new intent in the Wit.ai app. After creation, train the intent by adding utterances.

update_app

Update App

Update an existing Wit.ai app's configuration such as name, language, timezone, description, or privacy settings. Call list_apps to discover accessible app IDs.

update_entity

Update Entity

Update an existing entity's configuration, such as its name, roles, lookup strategies, or keywords.

create_app_tag

Create App Tag

Create a new version tag for a Wit.ai app. Call list_apps to discover accessible app IDs. Tags snapshot the current NLU model state for versioning.

get_trait

Get Trait

Get detailed information about a specific trait, including its possible values.

get_intent

Get Intent

Get detailed information about a specific intent, including its associated entities.

list_intents

List Intents

List all intents configured in the Wit.ai app. Returns intent names and IDs. Use this to explore available intents before analyzing text.

list_traits

List Traits

List all traits configured in the Wit.ai app. Traits are sentence-level classifiers (e.g., sentiment, politeness) that are distinct from entities.

delete_utterances

Delete Utterances

Delete training utterances from the Wit.ai app by their text content. Useful for cleaning up or correcting training data.

list_voices

List Voices

List available voices for text-to-speech synthesis. Returns voice names, locales, genders, and available styles.

manage_trait_values

Manage Trait Values

Add or remove possible values for an existing trait.

get_entity

Get Entity

Get detailed information about a specific entity, including its roles, lookup strategies, and keyword values.

delete_trait

Delete Trait

Permanently delete a trait from the Wit.ai app. This cannot be undone.

delete_intent

Delete Intent

Permanently delete an intent from the Wit.ai app. This cannot be undone.

analyze_text

Analyze Text

Extract meaning from text using Wit.ai's NLU engine. Returns detected **intents**, **entities**, and **traits** with confidence scores. Supports optional context (locale, timezone, reference time) for improved entity resolution. Use the `maxResults` parameter to get multiple candidate intents (N-best).

create_entity

Create Entity

Create a new custom entity in the Wit.ai app. Entities can be keyword-based (with explicit values) or free-text. Specify roles to distinguish how the entity is used in different contexts (e.g., "origin" vs "destination" for a location entity).

delete_entity

Delete Entity

Permanently delete an entity from the Wit.ai app. This cannot be undone.

create_trait

Create Trait

Create a new trait in the Wit.ai app with initial values. Traits are sentence-level classifiers such as sentiment, greeting detection, or custom categories.

list_entities

List Entities

List all entities configured in the Wit.ai app, including both built-in and custom entities. Returns entity names and IDs.

list_app_tags

List App Tags

List all version tags for a Wit.ai app. Call list_apps to discover accessible app IDs. Tags provide version control for your NLU models, allowing you to snapshot and reference specific model versions.

detect_language

Detect Language

Detect the language of a given text. Returns the N-best detected locales with confidence scores. Useful for routing multilingual inputs or selecting the correct NLP model.

delete_app

Delete App

Permanently delete a Wit.ai app. Call list_apps to discover accessible app IDs. This action cannot be undone.

train_utterances

Train Utterances

Submit training utterances (samples) to train the Wit.ai NLU model. Each utterance can include intent labels, entity annotations with character positions, and trait annotations. Useful for bulk importing training data.

create_app

Create App

Create a new Wit.ai app. Returns the new app's ID and server access token that can be used to interact with the app.

get_app

Get App

Get detailed information about a specific Wit.ai app by its ID. Call list_apps to discover accessible app IDs. Returns configuration, training status, and metadata.

manage_entity_keywords

Manage Entity Keywords

Add or remove keywords and synonyms for a keyword-type entity. Use this to expand the vocabulary of an entity by adding new canonical keywords with their synonym expressions, or to remove existing ones.

synthesize_speech

Synthesize Speech

Convert text to a downloadable audio file using a Wit.ai voice. Call list_voices to choose a supported voice and style.

Connect Witai to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Witai in Metorial. In your Metorial portal, enable the Witai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Witai tools.

Run Witai through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Witai and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Witai tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Witai

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Airtable

Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.

Sentry

Track, manage, and resolve application errors and performance issues. List, query, and bulk-update issues and error events with filters like status, assignment, and tags. Create and manage releases, associate commits, and upload source maps. Configure issue alert rules and metric alert rules with notification actions. Set up cron monitors to detect missed or failed scheduled jobs. Build custom dashboards with configurable widgets. Run ad-hoc Discover queries across errors and transactions for performance analysis. Manage organizations, teams, projects, and members. Provision users via SCIM. Access session replay data.

Bitbucket

Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.

Technical notes for Witai

Analyze text for intents, entities, and traits, detect languages, and synthesize downloadable speech with Wit.ai. Manage apps, model version tags, entities, intents, traits, and annotated training utterances, and export app configurations.

Frequently asked questions

Common questions about connecting Witai to AI agents with Metorial.

  1. How many tools does the Witai MCP server have?
    The Witai MCP server exposes 31 tools, including List Apps, List Utterances, Export App. Each one is governed and traced through Metorial.
  2. Witai exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Witai MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Witai and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Witai MCP server yourself or use the hosted gateway.

Connect Witai to production AI agents

See how Metorial gives your team governed access to Witai, with tracing and security controls built in.

Book a demoDeploy Witai