Cursor MCP integration for AI agents.
Connect AI agents to Cursor through 4 structured actions, including get daily usage data, get team spend, and list audit logs. Review authentication, inputs…
- ACTION CONTRACTS
- 4
- 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 Cursor integration exposes
The Cursor Agent App exposes 4 provider-backed actions for developer tools and ai work. Its current contract lets an authorized agent retrieve cursor daily usage metrics for a team over a date range of up to 30 days, retrieve cursor team spending for the current billing cycle with optional search, sort, and pagination, and list cursor team audit log events with optional time, event type, user, search, and page 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 Cursor account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Cursor capabilities.
Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_daily_usage_dataREADRetrieve Cursor daily usage metrics for a team over a date range of up to 30 days.
INPUTS: startDate / endDate / page / pageSize
get_team_spendREADRetrieve Cursor team spending for the current billing cycle with optional search, sort, and pagination.
INPUTS: searchTerm / sortBy / sortDirection / page / pageSize
list_audit_logsREADList Cursor team audit log events with optional time, event type, user, search, and page filters.
INPUTS: startTime / endTime / eventTypes / search / page
list_team_membersREADList Cursor team members visible to the team API key.
INPUT CONTRACTS
Know what the action needs before it runs.
get_daily_usage_data
startDateREQUIRED- The inclusive start date in epoch milliseconds.
endDateREQUIRED- The inclusive end date in epoch milliseconds.
pageOPTIONAL- The 1-indexed page number to request.
pageSizeOPTIONAL- The number of users to return per page.
get_team_spend
searchTermOPTIONAL- Search text matched against user names and emails.
sortByOPTIONAL- The field used to sort spending rows.
sortDirectionOPTIONAL- The sort direction for spending rows.
pageOPTIONAL- The 1-indexed page number to request.
pageSizeOPTIONAL- The number of spending rows to return per page.
list_audit_logs
startTimeOPTIONAL- The start time as a Cursor date shortcut, ISO timestamp, date, or Unix timestamp.
endTimeOPTIONAL- The end time as a Cursor date shortcut, ISO timestamp, date, or Unix timestamp.
eventTypesOPTIONAL- Cursor audit event types to include.
searchOPTIONAL- A search term used to filter audit events.
pageOPTIONAL- The 1-indexed page number to request.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Daily Usage Data
Retrieve Cursor daily usage metrics for a team over a date range of up to 30 days. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_daily_usage_dataVerify with Get Team Spend
Retrieve Cursor team spending for the current billing cycle with optional search, sort, and pagination. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_team_spendSAFETY BOUNDARY
Operate Cursor with explicit limits
- Authorize Cursor with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Cursor 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 Cursor rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Cursor task completed successfully.
CONNECTION MODEL
API key
Cursor API key sent with Basic authentication. Create or copy a key from Cursor Dashboard > API Keys: https://cursor.com/dashboard/api
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
- 0
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 Cursor.