Model Context Protocol (MCP) server for freee API integration
Plain Insurance 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
Business insurance quotes for Danish companies, active policies and unsigned offers for review.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http plain-insurance-mcp https://app.plain.insurance/api/mcp
# 2 — ask your agent for something these tools do
# list_onboarding_catalog, quote_onboarding_products, create_onboarding and 5 more
Plain Insurance 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 plain-insurance-mcp https://app.plain.insurance/api/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.
8 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.
Lists the insurance products a Danish company can be offered and the questions to answer before quoting. Pass the company's CVR to resolve industry-specific questions and options. Use product slugs in products and question names as keys in answers. Employee FTE questions are listed as two whole-number questions, <name>.fullTime and <name>.partTime, each from 0 to 9999 inclusive; when requi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| region | string | no | Market. Only Denmark (dk) is supported. Optional; defaults to dk. |
| cvr | string | no | Danish company registration number (CVR), eight digits, e.g. 39488914. |
Calculates indicative prices for up to twenty products for the company with this CVR, from one flat answers object. A plain key answers a question for the company and for every selected product that asks it; <product>.<name> answers one product's question. Stored answers and company discounts are not reused; supply required answers explicitly. An optional partnerCode applies that partner's dis
| Parameter | Type | Required | Notes |
|---|---|---|---|
| region | string | no | Market. Only Denmark (dk) is supported. Optional; defaults to dk. |
| cvr | string | yes | Danish company registration number (CVR), eight digits, e.g. 39488914. |
| startDate | string | no | Policy start date (YYYY-MM-DD). Defaults to today. Must be between today and one year ahead. |
| partnerCode | string | no | Optional partner discount code, 2-64 letters, digits, hyphens or underscores. Must be active. |
| products | array | yes | The products to quote: 1 to 20 distinct slugs, including any products they require. |
| answers | object | yes | Every answer in one object, keyed by the catalog question name. A plain name answers that question for the company and for every selected product that asks it; <product>.<name> (e.g. loesoereforsi |
Recalculates an approved quote and creates offered, unsigned policies, ready for the customer to review and sign on Plain. Send the exact quote request again with its quoteId before expiresAt; offers are created for the products with status.value quoted only. Active insurance is rechecked before creation. Retry a failed request on the same connection with the same idempotency key and body. No insu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quote | object | yes | The company, products and answers to price. Send the same object again in /start. |
| string | no | Email address of the person signing up; a verification code is sent here. | |
| name | string | no | Full name of the person signing up. Must not contain links or markup. |
| quoteId | string | yes | The quoteId of the quote the person approved. |
| idempotencyKey | string | no | Random key of 32-128 letters, digits, hyphens or underscores. Retry a failed request with the same key and body. |
Confirms the signup email with the eight-digit code the person received. Codes expire after 15 minutes and allow five attempts. Keep the returned capability and continuationToken private. Does not activate insurance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| onboardingId | string | yes | From the /start result. |
| capability | string | yes | From the /start result. |
| code | string | yes | The eight-digit code from the verification email. Valid for 15 minutes, five attempts. |
Returns a one-time link, valid for five minutes, where the person reviews the offers and sets up payment on Plain. The person must open and confirm it. Setting up payment does not accept the offers or charge money. Use the same authorized connection that created the offers and keep the target company selected; continuationToken may then be omitted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| onboardingId | string | yes | From the /start result. |
| capability | string | yes | From the /start result. |
| continuationToken | string | no | The continuationToken from the /verify-email result. |
Requires signing in to Plain; calling it prompts sign-in when needed. Lists companies explicitly approved for this Plain connection that you still have access to, and marks the active company. Reports granted scopes and whether the connection can create unsigned offers. Check this before quoting for an existing company or offering to create offers. Reconnect requesting onboarding:write to approve
No parameter schema on file.
Requires signing in to Plain. Changes the active Plain company for subsequent tool calls on this connection. Use an exact companyId from list_companies. All chats sharing this authorization share the selection. Already-running requests may finish for the previous company.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| companyId | string | yes | — |
Requires signing in to Plain; calling it prompts sign-in when needed. Lists the active insurance policies for the currently selected Plain company on this connection, including product, carrier, dates, price and billing details. Amounts are in major currency units (e.g. DKK). totalPrice is the total price the customer pays; it is legally required to be split into the insurance premium and fees (st
No parameter schema on file.
- 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 Plain Insurance 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 |
|---|---|---|
| list_onboarding_catalog | no tags | |
| quote_onboarding_products | no tags | |
| create_onboarding | state-write | state-write: declares readOnlyHint: false |
| verify_onboarding_email | state-write | state-write: declares readOnlyHint: false |
| get_onboarding_payment_link | state-write | state-write: declares readOnlyHint: false |
| list_companies | no tags | |
| set_company_context | state-write | state-write: declares readOnlyHint: false |
| list_active_policies | no tags |
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 1.0.0.
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 Plain Insurance 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.