# Wit.ai — MCP server on mcp.ai
> Connect your Wit.ai account and use 31 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Wit.ai is a natural language processing platform that enables developers to build applications and devices that understand human language.

By: mcp.ai · official
Page: https://mcp.ai/wit_ai

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_wit_ai?ms=1787293500000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/wit_ai/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/wit_ai/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/wit_ai/skill.md
Postman collection (v2.1): https://mcp.ai/wit_ai/postman.json

## Tools
- wit_ai_add_entity_keyword(entity: string, keyword: string, synonyms?: string[]) — Tool to add a keyword with optional synonyms to a Wit.ai entity. Use when extending entity values.
- wit_ai_add_keyword_synonym(entity: string, keyword: string, synonym: string) — Tool to add a new synonym to a keyword in an entity. Use when expanding entity keyword recognition with additional terms.
- wit_ai_add_trait_value(trait: string, value: string) — Tool to add a new value to an existing trait in Wit.ai. Use when extending trait vocabulary with additional values.
- wit_ai_create_app(lang: string, name: string, private?: boolean) — Tool to create a new app in Wit.ai. Use when you need to programmatically initialize an application before training or importing data.
- wit_ai_create_entity(name: string, roles: string[], lookups?: string[], keywords?: object[]) — Tool to create a new entity in Wit.ai. Use when defining custom entity types for natural language understanding.
- wit_ai_create_intent(name: string) — Tool to create a new intent in Wit.ai. Use when you need to define a new intent for natural language understanding.
- wit_ai_create_trait(name: string, values: object[], lookups?: string[], mutually_exclusive?: boolean) — Tool to create a new trait in Wit.ai. Use when defining custom entity attribute matching behavior.
- wit_ai_create_utterances(utterances: object[]) — Tool to add training utterances (samples with annotations) to your Wit.ai app. Use when you need to train your model with labeled examples. Rate limit: 200 samples per minute.
- wit_ai_delete_app(app_id: string, access_token?: string) — Tool to delete a specific app from wit.ai. Use when you need to remove an existing app by its ID after confirming its existence.
- wit_ai_delete_entity(entity: string) — Tool to permanently delete an entity by name. Use when you need to remove an existing entity from the wit.ai app.
- wit_ai_delete_entity_keyword(entity: string, keyword: string) — Tool to delete a keyword from a keywords entity in wit.ai. Use when you need to remove a specific keyword from an entity.
- wit_ai_delete_entity_role(role: string, entity: string) — Tool to delete a specific role from an entity in wit.ai. Use when you need to remove a role association from an entity.
- wit_ai_delete_intent(intent: string) — Tool to permanently delete an intent by name. Use when you need to remove an intent from the app.
- wit_ai_delete_keyword_synonym(entity: string, keyword: string, synonym: string) — Tool to delete a synonym from a keyword in an entity. Use when you need to remove a specific synonym mapping from an entity keyword.
- wit_ai_delete_utterances(utterances: object[]) — Tool to delete validated utterances (training samples) from your Wit.ai app. Use when you need to remove specific training data.
- wit_ai_detect_language(n?: integer, q: string) — Tool to detect the language of a given text input. Returns detected locales with confidence scores. Use when you need to identify the language of user-provided text.
- wit_ai_export_app() — Tool to export Wit.ai app data as a backup ZIP file. Returns a download URL for the backup file containing all app data.
- wit_ai_get_app(app_id: string, access_token?: string) — Tool to retrieve metadata and settings of a Wit.ai app. Use when you need to fetch complete app details by app ID after authenticating.
- wit_ai_get_entity(entity: string) — Tool to retrieve details of a specific entity including keywords and roles. Use when you need entity metadata by ID or name.
- wit_ai_get_intent(intent_id: string) — Tool to retrieve details of a specific intent. Use when you need full intent metadata given its ID.
- wit_ai_get_intents(limit?: integer, offset?: integer) — Tool to list all intents in a Wit.ai app. Use after authenticating to retrieve defined intents.
- wit_ai_get_message(n?: integer, q: string, context?: string) — Tool to analyze a text message and extract its intent, entities, and traits. Use when you need structured meaning from user input.
- wit_ai_get_trait(trait_id: string) — Tool to retrieve details of a specific trait. Use when you have the trait ID and need its full metadata.
- wit_ai_get_traits(v?: string) — Tool to list all traits in a Wit.ai app. Use after authenticating to retrieve defined traits.
- wit_ai_get_voice(voice: string) — Tool to retrieve details for a specific text-to-speech voice. Use when you need information about available styles and parameters for a voice.
- wit_ai_list_app_tags(app: string) — Tool to retrieve all tag groups (versions) for a Wit.ai app. Use when you need to list available versions or snapshots of an app's state.
- wit_ai_list_apps(limit: integer, offset?: integer) — Tool to retrieve the list of all Wit.ai apps for the authenticated user. Use when you need to fetch apps with pagination support.
- wit_ai_list_entities() — Tool to list all entities in a Wit.ai app. Use after authenticating to retrieve defined entities.
- wit_ai_list_utterances(limit?: integer, offset?: integer, traits?: string[], intents?: string[], entities?: string[]) — Tool to retrieve training utterances (samples) from a Wit.ai app. Use when you need to view or analyze the app's training data. Supports filtering by intents, entities, and traits.
- wit_ai_list_voices() — Tool to retrieve all available text-to-speech voices grouped by locale. Use when you need to discover which voices are available for speech synthesis.
- wit_ai_put_app(body: object, app_id: string, access_token?: string) — Tool to update an existing Wit.ai app. Use when you need to modify app settings after creation.

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

## Links
Docs: https://mcp.ai/docs/mcps/wit_ai
Website: https://mcp.ai/mcps/wit_ai