Wit.ai MCP integration for AI agents.
Connect AI agents to Wit.ai through 20 structured actions, including get app, add entity keyword, delete utterances, and analyze message. Review authenticati…
- ACTION CONTRACTS
- 20
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Wit.ai integration exposes
The Wit.ai Agent App exposes 20 provider-backed actions for ai and developer tools work. Its current contract lets an authorized agent retrieve details and training status for a specific wit.ai app, add a keyword and optional synonyms to an existing wit.ai entity, and asynchronously delete validated utterances from the current wit.ai app. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Wit.ai account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Wit.ai capabilities.
Showing 12 of 20 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_appREADRetrieve details and training status for a specific Wit.ai app.
INPUTS: appId
add_entity_keywordWRITEAdd a keyword and optional synonyms to an existing Wit.ai entity.
INPUTS: entityName / keyword / synonyms
delete_utterancesHIGH IMPACTAsynchronously delete validated utterances from the current Wit.ai app.
INPUTS: utterances
analyze_messageREVIEWAnalyze a text message and return the intents, entities, and traits inferred by Wit.ai.
INPUTS: text / topN / tag / context / dynamicEntities
add_keyword_synonymWRITEAdd a synonym to a specific keyword on a Wit.ai entity.
INPUTS: entityName / keyword / synonym
add_trait_valueWRITEAdd a canonical value to an existing Wit.ai trait.
INPUTS: traitName / value
create_entityWRITECreate a new Wit.ai entity with optional lookups and keywords.
INPUTS: name / roles / lookups / keywords
create_intentWRITECreate a new Wit.ai intent for labeling user messages.
INPUTS: name
create_traitWRITECreate a new Wit.ai trait with one or more canonical values.
INPUTS: name / values / lookups / mutuallyExclusive
create_utterancesWRITEAsynchronously enqueue validated utterances for training in Wit.ai.
INPUTS: utterances
detect_languageREVIEWDetect the most likely locales for a text message using Wit.ai language identification.
INPUTS: text / topN
get_entityREADRetrieve a Wit.ai entity including its roles, lookups, and keywords.
INPUTS: entityName
INPUT CONTRACTS
Know what the action needs before it runs.
get_app
appIdREQUIRED- Wit.ai app ID.
add_entity_keyword
entityNameREQUIRED- Entity name or ID.
keywordREQUIRED- Keyword value.
synonymsOPTIONAL- Synonyms for the new keyword.
delete_utterances
utterancesREQUIRED- Validated utterances to delete asynchronously.
analyze_message
textREQUIRED- User text sent to Wit.ai for analysis.
topNOPTIONAL- Maximum number of top candidates to request from Wit.ai.
tagOPTIONAL- Specific Wit.ai app version tag to query.
contextOPTIONAL- Context object used by Wit.ai for locale, timezone, and other hints.
dynamicEntitiesOPTIONAL- Dynamic entities injected into the request for one-off disambiguation.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get App
Retrieve details and training status for a specific Wit.ai app. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_appControl Add Entity Keyword
Add a keyword and optional synonyms to an existing Wit.ai entity. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
add_entity_keywordVerify with Add Entity Keyword
Add a keyword and optional synonyms to an existing Wit.ai entity. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
add_entity_keywordSAFETY BOUNDARY
Operate Wit.ai with explicit limits
- Authorize Wit.ai with API key and grant only the provider access required by the selected actions.
- 9 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Treat `delete_utterances` as high-impact operations and require an explicit approval boundary.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Wit.ai rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Wit.ai task completed successfully.
CONNECTION MODEL
API key
Wit.ai Bearer token used to access the HTTP API. Create or open your app at https://wit.ai/apps and copy the Server Access Token from the app settings.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 9
- WRITE SIGNALS
- 8
- HIGH IMPACT
- 1
- REVIEW SIGNALS
- 2
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Wit.ai.