Model Context Protocol (MCP) server for freee API integration
ExpenseOnDemand MCP by usefulapi is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Read exports, payroll totals and users; add, update or deactivate employees in ExpenseOnDemand.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http expenseondemand-mcp-by-usefulapi https://expenseondemand.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# expenseondemand_export_accounting, expenseondemand_get_payroll_export, expenseondemand_list_export_templates and 12 more
ExpenseOnDemand MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http expenseondemand-mcp-by-usefulapi https://expenseondemand.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Fetch approved expense data for an accounting integration, filtered by report, date range, category, claimant, cost centre, grade and payment type. Reads data only; the POST carries the filter body. Accounting API: POST /accounting/api/AccountingExport.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| exportReportId | integer | no | Export report id (one the organisation has; see expenseondemand_list_export_templates). |
| exportType | integer | no | 1 = new items, 2 = previously exported items. |
| fromDate | string | no | Start of the expense submission date range. |
| toDate | string | no | End of the expense submission date range. |
| expenseCategoryFilter | array | no | Expense category ids (list of ids; leave out for no filter). |
| claimantFilter | array | no | Claimant ids (list of ids; leave out for no filter). |
| costCenterFilter | array | no | Cost centre ids (list of ids; leave out for no filter). |
| claimantTypeFilter | array | no | Claimant type ids (list of ids; leave out for no filter). |
| gradeFilter | array | no | Grade ids (list of ids; leave out for no filter). |
| paymentTypeFilter | array | no | Payment type ids (list of ids; leave out for no filter). |
Get the total approved expense amount per employee for payroll: name, email, expense count and total amount. Accounting API: GET /accounting/api/PayrollExport.
No parameter schema on file.
List the export report types configured for the subscription, with their report ids and fields. Use a reportId as exportReportId in expenseondemand_export_accounting. Meta API: GET /meta/api/GetExportTemplates.
No parameter schema on file.
List the expense categories of the subscription with id, name, active flag and base category id. Meta API: GET /meta/api/GetExpenseCategoriesForOrganisation.
No parameter schema on file.
List the employee grades of the subscription with id, name and active flag. Meta API: GET /meta/api/GetGradesForOrganisation.
No parameter schema on file.
List the customers of the subscription with id, name, codes and active flag. Customer API: GET /customer/api/GetCustomersForOrganisation.
No parameter schema on file.
Add a customer to the subscription. The id is generated by ExpenseOnDemand. Creates a new record each call. Customer API: POST /customer/api/AddCustomerForSubscription.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Customer name. |
| code | string | no | Customer code 1. |
| code2 | string | no | Customer code 2. |
| isActive | boolean | no | Whether the customer is active. |
Update an existing customer by id. Send every field you want to keep: the vendor may clear fields you leave out, so read the record first with expenseondemand_list_customers. Customer API: POST /customer/api/UpdateCustomerForSubscription.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Id of the customer to update (from expenseondemand_list_customers). |
| name | string | no | Customer name. |
| code | string | no | Customer code 1. |
| code2 | string | no | Customer code 2. |
| isActive | boolean | no | Whether the customer is active. |
List the cost centres of the subscription with id, name, codes and active flag. Cost Centre API: GET /costCentre/api/GetCostCentresForOrganisation.
No parameter schema on file.
Add a cost centre to the subscription. The id is generated by ExpenseOnDemand. Creates a new record each call. Cost Centre API: POST /costCentre/api/AddCostCentreForSubscription.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Cost centre name. |
| code | string | no | Cost centre code 1. |
| code2 | string | no | Cost centre code 2. |
| isActive | boolean | no | Whether the cost centre is active. |
Update an existing cost centre by id. Send every field you want to keep: the vendor may clear fields you leave out, so read the record first with expenseondemand_list_cost_centres. Cost Centre API: POST /costCentre/api/UpdateCostCentreForSubscription.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Id of the cost centre to update (from expenseondemand_list_cost_centres). |
| name | string | no | Cost centre name. |
| code | string | no | Cost centre code 1. |
| code2 | string | no | Cost centre code 2. |
| isActive | boolean | no | Whether the cost centre is active. |
List the users (employees) of the subscription with email, name, status (1 Active, 2 Inactive, 3 NotInvited, 4 Pending, 5 Deleted), role and approver email. Users API: GET /users/api/GetUsersForOrganisation.
No parameter schema on file.
Add an employee to the subscription. ExpenseOnDemand treats the new employee as invited. Creates a record each call, so check expenseondemand_list_users first. Users API: POST /users/api/AddEmployee.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email ID of the employee. | |
| firstName | string | yes | First name of the employee. |
| lastName | string | yes | Last name of the employee. |
| employeeId | string | yes | Employee ID 1 (your HR or payroll id). |
| employeeId2 | string | no | Employee ID 2 (optional). |
| employeeId3 | string | no | Employee ID 3 (optional). |
| employeeId4 | string | no | Employee ID 4 (optional). |
| employeeRole | integer | yes | Role: 1 = Claimant, 2 = Approver, 3 = Finance Manager. |
| approverEmail | string | no | Email of the approver assigned to this employee. |
Update an existing employee, identified by email. Send every field you want to keep: the vendor may clear fields you leave out, so read the record first with expenseondemand_list_users. Users API: POST /users/api/UpdateEmployee.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email ID of the employee. | |
| firstName | string | yes | First name of the employee. |
| lastName | string | yes | Last name of the employee. |
| employeeId | string | yes | Employee ID 1 (your HR or payroll id). |
| employeeId2 | string | no | Employee ID 2 (optional). |
| employeeId3 | string | no | Employee ID 3 (optional). |
| employeeId4 | string | no | Employee ID 4 (optional). |
| employeeRole | integer | yes | Role: 1 = Claimant, 2 = Approver, 3 = Finance Manager. |
| approverEmail | string | no | Email of the approver assigned to this employee. |
Deactivate an employee by email, so they can no longer submit or approve expenses. Users API: POST /users/api/DeactivateEmployee.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email ID of the employee to deactivate. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ExpenseOnDemand MCP by usefulapi or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| expenseondemand_export_accounting | untrusted-input | untrusted-input: keyword "fetch" |
| expenseondemand_get_payroll_export | no tags | |
| expenseondemand_list_export_templates | no tags | |
| expenseondemand_list_expense_categories | no tags | |
| expenseondemand_list_grades | no tags | |
| expenseondemand_list_customers | no tags | |
| expenseondemand_add_customer | state-write | state-write: declares destructiveHint: true |
| expenseondemand_update_customer | no tags | |
| expenseondemand_list_cost_centres | no tags | |
| expenseondemand_add_cost_centre | state-write | state-write: declares destructiveHint: true |
| expenseondemand_update_cost_centre | no tags | |
| expenseondemand_list_users | no tags | |
| expenseondemand_add_employee | state-write | state-write: declares destructiveHint: true |
| expenseondemand_update_employee | no tags | |
| expenseondemand_deactivate_employee | state-write | state-write: declares destructiveHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.2.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish ExpenseOnDemand MCP by usefulapi can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.