Brex MCP integration for AI agents.
Connect AI agents to Brex through 9 structured actions, including get budget, get company, and get current user. Review authentication, inputs, workflows, an…
- ACTION CONTRACTS
- 9
- 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 Brex integration exposes
The Brex Agent App exposes 9 provider-backed actions for finance work. Its current contract lets an authorized agent retrieve one brex budget by id, retrieve the brex company associated with the connected user token, and retrieve the brex user associated with the connected user token. 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 Brex account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Brex capabilities.
Showing 9 of 9 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_budgetREADRetrieve one Brex budget by ID.
INPUTS: id
get_companyREADRetrieve the Brex company associated with the connected user token.
get_current_userREADRetrieve the Brex user associated with the connected user token.
get_expenseREADRetrieve one Brex expense by ID.
INPUTS: id / expand / loadCustomFields
list_budgetsREADList Brex budgets with cursor pagination.
INPUTS: cursor / limit
list_card_accountsREADList Brex card accounts for the connected company.
list_expensesREADList Brex expenses with documented filters and cursor pagination.
INPUTS: cursor / limit / expand / userIds / parentExpenseIds
list_primary_card_transactionsREADList settled transactions across all Brex card accounts with optional user and date filters.
INPUTS: cursor / limit / userIds / postedAtStart / expand
list_usersREADList Brex users with optional email, remote display ID, and cursor filters.
INPUTS: cursor / limit / email / remoteDisplayId / expand
INPUT CONTRACTS
Know what the action needs before it runs.
get_budget
idREQUIRED- The Brex resource identifier.
get_expense
idREQUIRED- The Brex resource identifier.
expandOPTIONAL- Brex expandable fields to include in the response.
loadCustomFieldsOPTIONAL- Whether Brex should load custom fields for the expense.
list_budgets
cursorOPTIONAL- The Brex cursor returned from a previous list response.
limitOPTIONAL- Maximum number of records to return.
list_expenses
cursorOPTIONAL- The Brex cursor returned from a previous list response.
limitOPTIONAL- Maximum number of expenses to return.
expandOPTIONAL- Brex expandable fields to include in the response.
userIdsOPTIONAL- Brex user IDs to filter expenses by.
parentExpenseIdsOPTIONAL- Parent expense IDs to filter itemized expenses by.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Budget
Retrieve one Brex budget by ID. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_budgetVerify with Get Company
Retrieve the Brex company associated with the connected user token. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_companySAFETY BOUNDARY
Operate Brex with explicit limits
- Authorize Brex with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned Brex 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 Brex rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Brex task completed successfully.
CONNECTION MODEL
API key
Brex user token sent as an Authorization: Bearer header. Create or revoke tokens in Brex Dashboard developer settings: https://dashboard.brex.com/settings/developer.
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
- 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 Brex.