Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Claim Done 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
Australian legal documents drafted from your answers for a flat fee. Not a law firm.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http claim-done-mcp https://claimdone.com.au/mcp
# 2 — ask your agent for something these tools do
# list_services, match_problem, start_document and 4 more
Claim Done 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 claim-done-mcp https://claimdone.com.au/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.
7 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.
Every document Claim Done drafts, with its live flat price in AUD, what the person receives and how it is delivered.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Optional word to filter by, e.g. "tenant", "invoice", "tribunal". |
Takes a plain-English description of the person's problem (who, what happened, what they want) and returns the Claim Done document that fits, its price in AUD, and what it does.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| problem | string | yes | The situation in the person's own words, 10 to 500 characters. |
Creates a Claim Done case for a document and returns the questions the person needs to answer, with a case_id and access_token for the later steps. Nothing is charged at this step.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| service | string | yes | Service slug from list_services or match_problem, e.g. "letter-of-demand". |
| state | string | yes | The person's Australian state or territory. |
| what_happened | string | yes | What happened, in the person's words (2 to 6 sentences). |
| your_name | string | yes | The person's full name or business name, as it should appear on the document. |
| your_email | string | yes | The person's email address: the draft, the receipt and the dashboard link go there. |
Saves the person's answers (question key => answer) for a case. Returns any questions still open, any follow-up questions the drafting needs, and ready_to_pay when the document can be drafted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | The case id returned by start_document. |
| access_token | string | yes | The access_token returned by start_document. |
| answers | object | yes | Question key => the person's answer. For a question with choices, pass one choice exactly. |
Returns a hosted Stripe Checkout URL for the case at the live flat price, for the person to pay. The document is drafted automatically once payment goes through, usually within about 5 minutes. If the case carries an eligibility notice, the notice is returned and acknowledge_notice must be true before a link is issued.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | The case id returned by start_document. |
| access_token | string | yes | The access_token returned by start_document. |
| acknowledge_notice | boolean | no | Set true after the person has heard the eligibility notice returned by answer_questions or a previous call. |
| registered_post | boolean | no | Add registered post delivery of a letter (extra fee, shown in list_services). |
Whether the case is paid, whether the draft is ready, and the dashboard link where the person reads, edits and approves it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | The case id returned by start_document. |
| access_token | string | yes | The access_token returned by start_document. |
After payment: the full text of each drafted document, plus the dashboard link where the person reads, edits and approves it (and, for letters, has it sent). Documents are never sent without the person's approval on the dashboard.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| case_id | integer | yes | The case id returned by start_document. |
| access_token | string | yes | The access_token returned by start_document. |
- 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 Claim Done 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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 1.0.0.
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 Claim Done 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.