Attention MCP integration for AI agents.
Connect AI agents to Attention through 5 structured actions, including get conversation, ask attention, and list conversations. Review authentication, inputs…
- ACTION CONTRACTS
- 5
- 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 Attention integration exposes
The Attention Agent App exposes 5 provider-backed actions for ai and communication work. Its current contract lets an authorized agent retrieve one attention conversation by internal conversation id or external import id, ask attention to analyze selected conversations or a deal using a natural-language prompt, and retrieve a paginated list of attention conversations with optional owner, participant, team, crm, and status filters. 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 Attention account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Attention capabilities.
Showing 5 of 5 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_conversationREADRetrieve one Attention conversation by internal conversation ID or external import ID.
INPUTS: id / by / includeInternalParticipants / includeZoomMetadata / includeImportMetadata
ask_attentionREVIEWAsk Attention to analyze selected conversations or a deal using a natural-language prompt.
list_conversationsREADRetrieve a paginated list of Attention conversations with optional owner, participant, team, CRM, and status filters.
INPUTS: fromDateTime / toDateTime / page / size / ownerIds
list_teamsREADList teams in the Attention organization.
list_usersREADList Attention users with optional user ID, email, team, and deleted-user filters.
INPUTS: ids / emails / teamUUID / includeDeleted
INPUT CONTRACTS
Know what the action needs before it runs.
get_conversation
idREQUIRED- Unique identifier of the conversation to retrieve.
byOPTIONAL- How to look up the conversation ID.
includeInternalParticipantsOPTIONAL- Whether to include internal participants in the response.
includeZoomMetadataOPTIONAL- Whether to include Zoom metadata in the response.
includeImportMetadataOPTIONAL- Whether to include import metadata in the response.
list_conversations
fromDateTimeOPTIONAL- Start date and time for filtering conversations.
toDateTimeOPTIONAL- End date and time for filtering conversations.
pageOPTIONAL- Page number for pagination, starting from 1.
sizeOPTIONAL- Number of conversations to return, from 1 to 50.
ownerIdsOPTIONAL- Owner user IDs to filter conversations.
list_users
idsOPTIONAL- User IDs to include.
emailsOPTIONAL- User email addresses to include.
teamUUIDOPTIONAL- Team UUID to filter users.
includeDeletedOPTIONAL- Whether to include deleted users.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Conversation
Retrieve one Attention conversation by internal conversation ID or external import ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_conversationVerify with List Conversations
Retrieve a paginated list of Attention conversations with optional owner, participant, team, CRM, and status filters. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_conversationsSAFETY BOUNDARY
Operate Attention with explicit limits
- Authorize Attention with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Attention data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Attention rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Attention task completed successfully.
CONNECTION MODEL
API key
Attention API key sent as a Bearer token. Admins can create and manage keys from the Attention API Keys settings page: https://app.attention.tech.
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
- 4
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 1
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 Attention.