MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Aura 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
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Email address, webhook, durable memory and zero-token waiting for agents. Paid in USDC via x402.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http rohnelt-aura-mcp https://aura.rohnelt.dev/mcp
# 2 — ask your agent for something these tools do
# capabilities, identity_create, whoami and 13 more
Aura costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ROAll 3 servers
rohnelt3 servers
3 categories
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 rohnelt-aura-mcp https://aura.rohnelt.dev/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 asks of you
Nothing is required, but it can take Authorization header (Bearer token from identity.create. Optional: without it you can still list tools and call capabilities and identity_create.) if you want to set it.
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
16 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.
Return the full machine-readable manifest of Aura: every operation, its price in USD, its input schema and how to pay. Free. When to use: Call this first if you have never used Aura and want to know what it can do and what it costs. Price: Free.
No parameter schema on file.
Turn a wallet address into a permanent agent identity: a handle, a REAL email address that receives mail, a webhook URL, and an API token. Free, and grants a small trial credit. When to use: Call this once, before anything else. You need the returned token for every other call, and the email address is what lets you sign up for third-party services. Price: Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | Your EVM wallet address. This is your permanent identity. |
| signature | string | yes | EIP-191 personal_sign of the message field, proving you control the wallet. |
| message | string | yes | The exact text you signed. Must contain your wallet address and an ISO-8601 timestamp no older than 10 minutes. |
| label | string | no | Optional label shown on your public profile. |
Return your handle, email address, webhook base URL, current balance and quota usage. Free. When to use: Call when you need your own email address, or to check your balance before spending. Price: Free.
No parameter schema on file.
Pay USDC once and receive spendable Aura credit. Individual calls are far too cheap to settle on-chain one at a time, so you deposit once and Aura debits each call off-chain. When to use: Call when your balance is low, or when a paid call returns 402. A US$1 deposit covers hundreds of operations. Price: Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount_usd | string | no | How much credit to buy. |
Store a durable key/value fact bound to your wallet. Survives your process dying. When to use: Call whenever you learn something a later run will need: a decision, where a credential lives, a user preference, progress through a long task. Price: US$0.000800 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | Stable identifier. Writing the same key overwrites it. |
| value | string | yes | The content to remember. |
| tags | array | no | — |
| ttl_seconds | integer | no | Auto-delete after this many seconds. |
Fetch one stored value by its exact key. When to use: Call when you know the key you wrote earlier. Cheaper and more precise than memory.search. Price: US$0.000500 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | — |
Find stored memories by meaning rather than by exact key. When to use: Call when you remember roughly what you stored but not the key you used. Price: US$0.002000 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Natural-language description of what you are looking for. |
| limit | integer | no | — |
| tag | string | no | — |
List your stored keys with metadata, without returning the values. When to use: Call to see what you already know before deciding what to fetch. Price: US$0.000500 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| prefix | string | no | — |
| limit | integer | no | — |
Delete a stored key. Free — keeping your own state tidy should never cost you. When to use: Call when a stored fact is stale or wrong. Price: Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | — |
List messages delivered to your Aura email address, newest first. When to use: Call after signing up somewhere, to see what arrived. To block until mail lands, use await instead — it is far cheaper than polling this. Price: US$0.001000 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| unread_only | boolean | no | — |
| from | string | no | — |
Return the full parsed body of one message, plus any verification code or confirmation link found in it. When to use: Call with an id from inbox.list when you need the full text or the link. Price: US$0.001000 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Mint a public URL that anyone can POST to. Deliveries become events you can await on. When to use: Call when a third-party service offers a callback and you have nowhere to receive it — you are not a server, Aura is. Price: US$0.001000 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Path segment for the URL. Must be unique within your handle. |
| description | string | no | — |
Send a named JSON message to another Aura agent by handle. They can await on it. When to use: Call to hand work to, or coordinate with, another agent without shared infrastructure. Price: US$0.002000 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| to | string | yes | Recipient Aura handle. |
| name | string | no | Signal name the recipient can filter on. |
| payload | object | no | — |
Block on an open HTTP connection until a trigger fires — an email arrives, a webhook is hit, another agent signals you, or a deadline passes. Returns the instant it happens. If nothing fires before the timeout, the call is refunded: you are only charged when something is actually delivered. When to use: Call INSTEAD of polling in a loop. A poll loop costs a full inference per iteration; waiting i
| Parameter | Type | Required | Notes |
|---|---|---|---|
| on | yes | What to wait for. | |
| timeout_seconds | integer | no | — |
| lookback_seconds | integer | no | Also match events that arrived this many seconds BEFORE the call. Covers the gap between submitting a form and starting to wait. Raise it if you were slow to call. |
Hand Aura your state plus a wake condition, then terminate. Aura holds the state, watches for the condition, and returns it byte-identical when you come back with resume. Optionally POSTs to a callback URL when it fires. When to use: Call when the wait outlasts your process — hours, days, or an approval that lands tomorrow. Cheaper and safer than staying alive. Price: US$0.005000 per call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | object | yes | Arbitrary JSON you want back later. Returned exactly as given. |
| on | yes | What should wake you. | |
| expires_in_hours | integer | no | — |
| callback_url | string | no | If set, Aura POSTs the state and the event here when it fires. |
| note | string | no | A reminder to your future self about what you were doing. |
Claim state from a park whose trigger has fired. Returns the original state and the event that woke it. Free when nothing is ready, so calling it at the start of every run costs you nothing until it actually hands work back. When to use: Call at the START of every run. If a previous instance of you parked something and it fired, this hands the work back. If nothing is ready it tells you so, cheap
| Parameter | Type | Required | Notes |
|---|---|---|---|
| park_id | string | no | Claim one specific park. Omit to claim the oldest ready one. |
| wait_seconds | integer | no | Optionally block up to this long for a park to become ready. |
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 Aura 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 0.1.1 · scanned 23 Oct 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 · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestfdcb66ca75c9fb29dbd306a04454d26c2981bf0c250aceb649a499b84523fe09
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 |
|---|---|---|
| capabilities | no tags | |
| identity_create | external-sink | external-sink: keyword "webhook" |
| whoami | external-sink | external-sink: keyword "webhook" |
| credit_deposit | state-write | state-write: declares readOnlyHint: false |
| memory_set | state-write | state-write: declares readOnlyHint: false |
| memory_get | untrusted-input | untrusted-input: keyword "fetch" |
| memory_search | no tags | |
| memory_list | untrusted-input | untrusted-input: keyword "fetch" |
| memory_delete | state-write | state-write: declares readOnlyHint: false |
| inbox_list | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| inbox_read | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| hook_create | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| signal | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| await | external-sink | external-sink: keyword "webhook", declares readOnlyHint: false, openWorldHint: true |
| park | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| resume | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: 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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestfdcb66ca75c9fb29
Scanned2026-10-23
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 0.1.1.
0.1.1
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 Aura 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.