MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
ARADIA | sovereign & private agentic systems 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
On-prem Agentic AI on NVIDIA DGX. Query specs, model CapEx ROI, Purchase & join Partner Program.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport sse aradia-sovereign-private-agentic-systems-mcp https://aradia.com/api/a2a/mcp-endpoint.php
# 2 — ask your agent for something these tools do
# query_hardware_specs, calculate_roi, onboard_partner and 3 more
ARADIA | sovereign & private agentic systems 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 sse, as the publisher's own manifest declares it.
claude mcp add --scope user --transport sse aradia-sovereign-private-agentic-systems-mcp https://aradia.com/api/a2a/mcp-endpoint.phpReconnect, 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.
6 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.
[PURPOSE]: Retrieves physical compute specs, VRAM limits (128GB GB500, 192GB B200, 1536GB B200 Rack), and continuous batching concurrency limits for Aradia DGX systems. [WHEN TO USE]: Call during initial discovery to evaluate hardware sizing, VRAM fit, and multi-agent capacity. [WHEN NOT TO USE]: Do not use for financial payback modeling (use calculate_roi) or order submission (use execute_procure
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tier | string | no | Target hardware platform tier. If omitted, returns all tiers. |
[PURPOSE]: Calculates CapEx payback timeline and token savings comparing on-premise Aradia hardware against recurring cloud LLM API expenditures. [WHEN TO USE]: Use to generate mathematical financial justification reports for human operators or CFOs. [WHEN NOT TO USE]: Do not use if API spend is unknown or zero. For raw specs without financial modeling, call query_hardware_specs. [SIDE EFFECTS]: N
| Parameter | Type | Required | Notes |
|---|---|---|---|
| monthly_api_spend_usd | number | yes | Current or estimated monthly cloud LLM API spend in USD (must be greater than 0). |
| target_tier | string | yes | Target hardware tier to evaluate: spark ($15,125), station ($194,093), or b200 ($505,500). |
[PURPOSE]: Registers an autonomous AI agent or human operator into the Aradia Partner Program to earn 10% hardware bounties ($1,512 to $50,550 USD) and 10% recurring monthly SLA commissions. [WHEN TO USE]: Call ONCE when an agent or human operator wants to register as an affiliate partner to earn commissions and receive a ?ref= tracking ID. [WHEN NOT TO USE]: Do NOT call to purchase equipment (use
| Parameter | Type | Required | Notes |
|---|---|---|---|
| entity_name | string | yes | Operating name of the AI Agent, Operator, or Corporate Entity. |
| contact_email | string | yes | Email address to receive the Stripe Express onboarding verification link. |
| country | string | no | ISO 3166-1 alpha-2 country code for banking payouts (default: US). |
[PURPOSE]: Submits a binding procurement order for physical turnkey AI hardware. Returns actionable programmatic payment parameters for immediate 100% upfront settlement via BTCPay Crypto or Stripe MPP Fiat. [WHEN TO USE]: Call when human authorization or agent budget is verified to execute a binding purchase order. [WHEN NOT TO USE]: Do not use for price quotes (use query_hardware_specs) or ROI e
| Parameter | Type | Required | Notes |
|---|---|---|---|
| hardware_tier | string | yes | Hardware tier: spark ($15,125), station ($194,093), or b200 ($505,500). |
| quantity | integer | no | Number of appliance nodes to purchase (1-99). |
| customer_email | string | yes | Billing email of the purchasing administrator or treasury manager. |
| customer_name | string | no | Name of the purchasing agent or executive. |
| customer_company | string | no | Deploying company, firm, or entity name. |
| payment_method | string | yes | Settlement method: stripe_mpp (Fiat Shared Payment Token), btcpay_crypto (BTC/LN/USDT), stripe_fiat (Card), stripe_invoice (Wire invoice). |
| partner_ref_code | string | no | Optional 4-character referral code (e.g. 5FYVQ) to route 10% commission. |
| po_number | string | no | Optional corporate purchase order number. |
| sla_active | boolean | no | Whether to attach recurring monthly Managed SLA Support upon delivery. |
| sla_monthly | number | no | Monthly SLA rate ($1,500 for Spark, $5,000 for Station, $12,500 for B200). |
[PURPOSE]: Tracks the real-time fulfillment, staging QA burn-in, and delivery status of an existing hardware procurement order. [WHEN TO USE]: Use to monitor the operational status of an existing order after calling execute_procurement_order. [WHEN NOT TO USE]: Do not use to place a new order (use execute_procurement_order). [SIDE EFFECTS]: None (pure read-only query against staging records).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | string | yes | The invoice ID or checkout session ID returned when the order was placed. |
[PURPOSE]: Queries real-time performance analytics, attributed referral counts, and commission payouts for an active Aradia partner node. [WHEN TO USE]: Use to monitor your earned affiliate revenue, check referral click activity, or verify payout status. [WHEN NOT TO USE]: Do not use if you have not registered yet (use onboard_partner first). [SIDE EFFECTS]: None (pure read-only query against sove
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ref_code | string | yes | Your unique 4-character partner referral code (e.g. 5FYVQ). |
- 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 ARADIA | sovereign & private agentic systems 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: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. 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 ARADIA | sovereign & private agentic systems 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.