Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
OffshoreProz Agent API 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.
93/100
tool-list score
14
tools declared
remote
at its publisher
—
calls last 7d
What it does
Developer MCP and REST API to form a Wyoming LLC or Marshall Islands DAO LLC.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http offshoreproz-agent-api-mcp https://api.offshoreproz.com/mcp
# 2 — ask your agent for something these tools do
# offshoreproz_list_jurisdictions, offshoreproz_get_jurisdiction_requirements, offshoreproz_estimate_cost and 11 more
OffshoreProz Agent API costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TBAll 2 servers
tcgtracker-boop2 servers
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
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.
Claude Codedeclared by this listing
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 offshoreproz-agent-api-mcp https://api.offshoreproz.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
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.
What you approve
14 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 all available company-formation jurisdictions with pricing and timelines. No sensitive data. Call this first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include_coming_soon | boolean | no | When true, also returns jurisdictions that are not yet accepting formations (status: coming_soon). Defaults to false. |
Return the required fields to form a company in a given jurisdiction.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction_code | string | yes | Short jurisdiction code to look up (e.g. WY for Wyoming, MI for Marshall Islands). Use offshoreproz_list_jurisdictions to discover available codes. |
Estimate the all-in cost for a jurisdiction. MUST be called before create_formation; returns an estimate_token required to create.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | Jurisdiction code to estimate for (e.g. WY, MI). Case-insensitive. |
| obtain_ein | boolean | no | Whether to include EIN (Employer Identification Number) obtainment in the estimate. Adds ~$99 USD and 2-4 extra business days. Defaults to true. |
Start forming a company. beneficial_owner = human custodian (authorized representative). For AI-agent formations, also pass owner_type='ai_agent' and agent_context.agent_id. Requires estimate_token from offshoreproz_estimate_cost AND user_confirmed_cost_and_process=true (user must have seen cost, timeline, KYC, payment, signature steps, and the not-legal-advice notice).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | Jurisdiction code where the company will be formed (e.g. WY, MI). Case-insensitive. |
| company_name | string | yes | Desired company name including entity suffix (e.g. 'Acme Trading LLC'). Availability is checked during formation. |
| obtain_ein | boolean | no | Whether to obtain an EIN (Employer Identification Number) from the IRS. Recommended for US banking. Adds ~$99 and 2-4 extra days. |
| estimate_token | string | yes | Short-lived cost-estimate token (est_*) returned by offshoreproz_estimate_cost. Required to confirm the user has seen the pricing. |
| user_confirmed_cost_and_process | boolean | yes | Must be true. Set this only after the user has explicitly acknowledged cost, timeline, KYC requirements, payment, DocuSeal signature, and the not-legal-advice notice. |
| owner_type | string | no | human (default) or ai_agent. For AI-initiated formations, set ai_agent and populate agent_context. |
| beneficial_owner | object | yes | Human custodian / authorized representative. Always a real person — subject to KYC and DocuSeal signing. |
| agent_context | object | no | AI entity metadata. Required when owner_type='ai_agent'. agent_id uniquely identifies the AI agent initiating or owning this formation. |
Get the current status and next action of a formation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| formation_id | string | yes | Formation ID to query (op_fm_* format). Returned by offshoreproz_create_formation or offshoreproz_list_formations. |
List documents available for a formation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| formation_id | string | yes | Formation ID whose documents to list (op_fm_* format). |
List all formations for the authenticated API key. Returns current status, jurisdiction, and next required actions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter by status (e.g. pending_owner_confirmation, kyc_pending, filed, complete, failed, cancelled) |
| jurisdiction | string | no | Filter by jurisdiction code (WY, MI, etc.) |
| limit | integer | no | Max results to return (default 20, max 100) |
Cancel a formation. Only possible from draft or pending_owner_confirmation status. Irreversible.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| formation_id | string | yes | Formation ID to cancel (op_fm_* format). The formation must be in draft or pending_owner_confirmation status. |
Reissue an expired or lost action link for the current formation step. The old link is invalidated.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| formation_id | string | yes | Formation ID for which to reissue the action link (op_fm_* format). The previous link is immediately invalidated. |
Create a free test API key instantly — no portal login required. Returns op_test_* key you can use immediately in this session. For production (op_live_*), complete email OTP verification via the portal. Call this first if you have no API key yet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Label for this key (e.g. 'my-agent-v1'). Helps identify it in the portal. |
| string | yes | Email address — used for formation notifications and live key OTP verification. |
Return the full audit trail / event log for a formation. Shows every status change, portal sync, webhooks, and notes. Useful for debugging or understanding where a formation is in the pipeline.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| formation_id | string | yes | Formation ID whose audit trail to retrieve (op_fm_* format). |
| limit | integer | no | Max events to return (default 50, max 500). Events are ordered newest-first. |
Retry a formation that is in 'failed' or 'action_required' status. Resets it to pending_owner_confirmation so the owner can restart the confirmation flow.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| formation_id | string | yes | Formation ID to retry (op_fm_* format). Must be in 'failed' or 'action_required' status. |
Register a webhook URL to receive real-time formation events (formation.created, formation.status_changed, formation.complete, etc.). Returns a signing secret (whsec_*) — store it to verify incoming payloads. Use '*' to receive all events.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | HTTPS URL that will receive POST requests for subscribed events. |
| events | array | yes | Event patterns to subscribe to. Use '*' for all events, 'formation.*' for all formation events, or specific types like 'formation.complete' or 'formation.status_changed'. |
| description | string | no | Optional human-readable label for this webhook endpoint (e.g. 'Production webhook'). |
List all registered webhook endpoints for the authenticated API key, including their event subscriptions and recent delivery stats.
No parameter schema on file.
Free
$0 forever
- 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 OffshoreProz Agent API or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 9 Nov 2026
Graded from the tools this server lists, not from its source code.
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.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest9ca2f88378c7e0cdfd9b07fb8c849b2ef4ed836c5b326fac8422a526b77e30b2
Score vectorthreat 100 → client 93
| 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 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
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.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
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 |
|---|---|---|
| offshoreproz_list_jurisdictions | no tags | |
| offshoreproz_get_jurisdiction_requirements | no tags | |
| offshoreproz_estimate_cost | no tags | |
| offshoreproz_create_formation | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| offshoreproz_get_formation_status | no tags | |
| offshoreproz_list_documents | no tags | |
| offshoreproz_list_formations | no tags | |
| offshoreproz_cancel_formation | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| offshoreproz_reissue_action_link | state-write | state-write: declares readOnlyHint: false |
| offshoreproz_register | state-write | state-write: declares readOnlyHint: false |
| offshoreproz_get_formation_events | no tags | |
| offshoreproz_retry_formation | state-write | state-write: declares readOnlyHint: false |
| offshoreproz_register_webhook | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, openWorldHint: true |
| offshoreproz_list_webhooks | external-sink | external-sink: keyword "webhook" |
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
Integrityfirst-seen
Surface digest9ca2f88378c7e0cd
Scanned2026-11-09
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.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
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.
Sign in to write one
Any signed-in account that does not publish OffshoreProz Agent API can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
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.