A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Harvest 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 time entries, projects, clients, tasks and invoices; log and update tracked time.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http usefulapi-harvest-mcp https://harvest.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# harvest_list_time_entries, harvest_get_time_entry, harvest_list_projects and 17 more
Harvest 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 usefulapi-harvest-mcp https://harvest.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.
20 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.
List time entries, optionally filtered by user, project, client, task, date range, running/billed status, or updated-since. Paginated. Harvest REST: GET /time_entries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | integer | no | Filter to a single user id. |
| client_id | integer | no | Filter to a single client id. |
| project_id | integer | no | Filter to a single project id. |
| task_id | integer | no | Filter to a single task id. |
| is_running | boolean | no | Only running (true) or only stopped (false) entries. |
| is_billed | boolean | no | Only billed (true) or unbilled (false) entries. |
| from | string | no | Only entries on/after this date, yyyy-mm-dd. |
| to | string | no | Only entries on/before this date, yyyy-mm-dd. |
| updated_since | string | no | Only entries updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
Retrieve a single time entry by id. Harvest REST: GET /time_entries/{id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| time_entry_id | integer | yes | The time entry id (required). |
List projects, optionally filtered by active status or client, or updated-since. Paginated. Harvest REST: GET /projects.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| is_active | boolean | no | Only active (true) or archived (false) projects. |
| client_id | integer | no | Filter to a single client id. |
| updated_since | string | no | Only projects updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
Retrieve a single project by id. Harvest REST: GET /projects/{id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | The project id (required). |
List clients, optionally filtered by active status or updated-since. Paginated. Harvest REST: GET /clients.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| is_active | boolean | no | Only active (true) or archived (false) clients. |
| updated_since | string | no | Only clients updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
Retrieve a single client by id. Harvest REST: GET /clients/{id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| client_id | integer | yes | The client id (required). |
List tasks (the billable/non-billable work categories that can be assigned to projects), optionally filtered by active status or updated-since. Paginated. Harvest REST: GET /tasks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| is_active | boolean | no | Only active (true) or archived (false) tasks. |
| updated_since | string | no | Only tasks updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
List users in the account, optionally filtered by active status or updated-since. Paginated. Harvest REST: GET /users.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| is_active | boolean | no | Only active (true) or archived (false) users. |
| updated_since | string | no | Only users updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
Retrieve the currently authenticated user (whom the access token belongs to). Harvest REST: GET /users/me.
No parameter schema on file.
List the authenticated user's active project assignments — the projects and their assignable tasks the current user can log time against (use this to find the project_id + task_id for harvest_create_time_entry). Paginated. Harvest REST: GET /users/me/project_assignments.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
List invoices, optionally filtered by client, project, state, date range, or updated-since. Paginated. Harvest REST: GET /invoices.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| client_id | integer | no | Filter to a single client id. |
| project_id | integer | no | Filter to a single project id. |
| state | string | no | Filter by invoice state: draft, open, paid or closed. |
| from | string | no | Only invoices issued on/after this date, yyyy-mm-dd. |
| to | string | no | Only invoices issued on/before this date, yyyy-mm-dd. |
| updated_since | string | no | Only invoices updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
Retrieve a single invoice by id, including its line items. Harvest REST: GET /invoices/{id}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| invoice_id | integer | yes | The invoice id (required). |
List estimates, optionally filtered by client, state, date range, or updated-since. Paginated. Harvest REST: GET /estimates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| client_id | integer | no | Filter to a single client id. |
| state | string | no | Filter by estimate state: draft, sent, accepted or declined. |
| from | string | no | Only estimates issued on/after this date, yyyy-mm-dd. |
| to | string | no | Only estimates issued on/before this date, yyyy-mm-dd. |
| updated_since | string | no | Only estimates updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
List expenses, optionally filtered by user, client, project, date range, billed status, or updated-since. Paginated. Harvest REST: GET /expenses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | integer | no | Filter to a single user id. |
| client_id | integer | no | Filter to a single client id. |
| project_id | integer | no | Filter to a single project id. |
| is_billed | boolean | no | Only billed (true) or unbilled (false) expenses. |
| from | string | no | Only expenses on/after this date, yyyy-mm-dd. |
| to | string | no | Only expenses on/before this date, yyyy-mm-dd. |
| updated_since | string | no | Only expenses updated since this ISO-8601 datetime. |
| page | integer | no | Page number (1-based) for pagination. |
| per_page | integer | no | Results per page (1–2000, Harvest default 2000). |
Retrieve the company/account settings for the authenticated account (name, currency, time/date formats, week start, feature flags). Harvest REST: GET /company.
No parameter schema on file.
Create a time entry. Requires project_id, task_id and spent_date. Provide hours to log a specific duration; OR provide started_time (+ optional ended_time) for a timestamped entry; OR omit both to start a running timer (on a timestamp-tracking account). Use harvest_list_project_assignments to find valid project_id + task_id. Harvest REST: POST /time_entries. WRITE — creates data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | The project id to log time against (required). |
| task_id | integer | yes | The task id within the project (required). |
| spent_date | string | yes | The date the time was spent, yyyy-mm-dd (required). |
| user_id | integer | no | Log on behalf of another user (defaults to the authenticated user; requires permission). |
| hours | number | no | Duration in decimal hours, e.g. 1.5. Omit to start a running timer. |
| started_time | string | no | Start time for a timestamped entry, e.g. '8:00am'. |
| ended_time | string | no | End time for a timestamped entry, e.g. '9:30am'. |
| notes | string | no | Notes for the time entry. |
Update an existing time entry's hours, notes, spent date, or project/task. Only the fields you provide are changed. Harvest REST: PATCH /time_entries/{id}. WRITE — modifies data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| time_entry_id | integer | yes | The time entry id to update (required). |
| project_id | integer | no | Reassign to a different project id. |
| task_id | integer | no | Reassign to a different task id. |
| spent_date | string | no | Change the date, yyyy-mm-dd. |
| hours | number | no | Change the duration in decimal hours, e.g. 2.25. |
| started_time | string | no | Change the start time, e.g. '8:00am'. |
| ended_time | string | no | Change the end time, e.g. '9:30am'. |
| notes | string | no | Change the notes. |
Stop a currently running time entry (no-op error if it is already stopped). Harvest REST: PATCH /time_entries/{id}/stop. WRITE — modifies data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| time_entry_id | integer | yes | The running time entry id to stop (required). |
Restart a previously stopped time entry, resuming its timer (error if it is already running). Harvest REST: PATCH /time_entries/{id}/restart. WRITE — modifies data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| time_entry_id | integer | yes | The stopped time entry id to restart (required). |
Permanently delete a time entry by id. This cannot be undone. Harvest REST: DELETE /time_entries/{id}. WRITE — destroys data.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| time_entry_id | integer | yes | The time entry id to delete (required). |
- 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 Harvest 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 |
|---|---|---|
| harvest_list_time_entries | no tags | |
| harvest_get_time_entry | no tags | |
| harvest_list_projects | no tags | |
| harvest_get_project | no tags | |
| harvest_list_clients | no tags | |
| harvest_get_client | no tags | |
| harvest_list_tasks | no tags | |
| harvest_list_users | no tags | |
| harvest_get_current_user | no tags | |
| harvest_list_project_assignments | no tags | |
| harvest_list_invoices | no tags | |
| harvest_get_invoice | no tags | |
| harvest_list_estimates | no tags | |
| harvest_list_expenses | no tags | |
| harvest_get_company | no tags | |
| harvest_create_time_entry | state-write | state-write: declares destructiveHint: true |
| harvest_update_time_entry | state-write | state-write: declares destructiveHint: true |
| harvest_stop_time_entry | state-write | state-write: declares destructiveHint: true |
| harvest_restart_time_entry | state-write | state-write: declares destructiveHint: true |
| harvest_delete_time_entry | 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 1.11.1.
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 Harvest 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.