Search, save and rate AI tools people shared in chats. Local catalogue, any model or none.
ZenVault 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
Wake-ups, webhook inboxes, TTL memory, watches and human approval for agents. Paid per call.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http zenvault-mcp https://api.zenvault.eu/mcp
# 2 — ask your agent for something these tools do
# create_wakeup, create_schedule, create_deadman and 41 more
ZenVault 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 zenvault-mcp https://api.zenvault.eu/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.
44 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.
Schedule a webhook call at a future time (one-shot). Your agent can die; the call still happens.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| at | string | yes | ISO-8601 time to fire |
| url | string | yes | webhook URL to call |
| payload | object | no | JSON to include |
Recurring webhook on a cron expression until the prepaid days run out.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cron | string | yes | cron expression, e.g. 0 7 * * * |
| url | string | yes | webhook URL |
| payload | object | no | — |
| days | number | no | prepaid days |
Dead-man switch: if you stop checking in, we fire your alert webhook.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | alert webhook |
| interval_seconds | number | no | max time between check-ins |
| days | number | no | — |
| apprise_url | string | no | optional human notification target |
Check in to a dead-man switch so it does not fire.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | dead-man switch id |
Hand over a payload now; we POST it to the target at a future moment.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| at | string | yes | ISO-8601 |
| url | string | yes | target URL |
| payload | object | no | — |
Dump up to 100 items now; we deliver them to your webhook at a fixed rate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | webhook |
| items | array | yes | items to drip |
| rate_seconds | number | no | — |
Signed proof that a hash (or your data) existed at this moment.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sha256 | string | no | hex digest |
| data | string | no | raw data to hash instead |
| note | string | no | — |
Fetch a URL and return content plus a signed receipt binding url, status, content hash and time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | URL to fetch |
| include_content | boolean | no | — |
Public URL that buffers inbound webhooks until you collect them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | number | no | prepaid days |
| label | string | no | — |
Collect buffered messages from an inbox, bin, front door or form.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | resource id |
| all | boolean | no | include already-collected |
Durable front door: buffers webhooks and forwards them to your gateway with retry-until-ack.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | your gateway URL |
| days | number | no | — |
| replay_hours | number | no | — |
Ask a human to approve or deny an action; returns a URL for them and a signed verdict for you. Times out as denied.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | what you want to do |
| detail | string | no | context for the human |
| timeout_seconds | number | no | — |
| webhook | string | no | called with the verdict |
| apprise_url | string | no | ping the human here |
Check whether a human approved or denied your request.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | approval id |
Send a message to a human on Telegram, Discord, Slack, ntfy, email and 100+ other services (apprise URL is used once, never stored).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| apprise_url | string | yes | apprise target URL |
| title | string | no | — |
| body | string | yes | message |
POST a payload to a URL, retried with backoff until it succeeds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | target |
| payload | object | no | — |
Create a key-value namespace with TTL that survives your runs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | number | no | — |
| label | string | no | — |
Store a value in a vault (max 1 MB).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | vault id |
| key | string | yes | — |
| value | string | yes | — |
Read a value from a vault.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | vault id |
| key | string | yes | — |
List keys in a vault.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | vault id |
Save run state so you can resume after a crash.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | checkpoint id |
| state | string | yes | serialized state |
Create a crash checkpoint store.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | number | no | — |
Load the latest saved checkpoint state.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Store a value that self-destructs on first read; returns a one-time read URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| value | string | yes | — |
| days | number | no | — |
Pull-based work queue with leases; timed-out leases requeue.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lease_seconds | number | no | — |
| max_attempts | number | no | — |
| days | number | no | — |
Push a job onto a queue.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | queue id |
| body | string | yes | job payload |
Lease the next job from a queue.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | queue id |
Acknowledge (or nack) a leased job.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | queue id |
| job_id | string | yes | — |
| action | string | no | — |
Create an atomic counter.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| start | number | no | — |
| days | number | no | — |
Increment a counter atomically.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| by | number | no | — |
Idempotency firewall: claim an operation id exactly once across runs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | firewall id |
| operation_id | string | yes | — |
Create an idempotency/replay firewall.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | number | no | — |
Publish an HTML page at name.zenvault.eu for N days.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| html | string | yes | page HTML |
| name | string | no | subdomain name |
| days | number | no | — |
Create an expiring share link with click stats.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | destination URL |
| days | number | no | — |
Watch something and fire your webhook when it changes. Types: change, keyword, regex, structured, drift, redirect, sitemap, staleness, rss, dns, port, cert, heartbeat.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | yes | watch type |
| url | string | no | URL to watch |
| webhook | string | yes | called on change |
| keyword | string | no | — |
| pattern | string | no | regex |
| selector | string | no | CSS selector or JSON path |
| json | boolean | no | — |
| percent | number | no | drift threshold |
| name | string | no | DNS name |
| record | string | no | DNS record type |
| host | string | no | — |
| port | number | no | — |
| domain | string | no | for cert watch |
| interval_seconds | number | no | — |
| confirmations | number | no | fire only after N consecutive hits |
| days | number | no | — |
Check a watch: last value, checks, fires.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Escalation chain: webhook, then after N seconds the next step, until acknowledged.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| steps | array | yes | steps: {webhook, apprise_url, wait_seconds} |
| subject | string | no | — |
| days | number | no | — |
Status of any resource you hold the management token for.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Extend a resource TTL by paying again.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| days | number | no | — |
Cancel a resource early.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Export everything under a resource before it expires.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Check the balance of your prepaid credit token.
No parameter schema on file.
Mint a spend-capped child token for a sub-agent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cap_usd | number | yes | hard spend cap |
| label | string | no | — |
| days | number | no | — |
Machine-readable price list for every ZenVault service, in USD.
No parameter schema on file.
Tell the operator what ZenVault is missing. Free.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| what | string | yes | what you need |
| why | string | no | why |
| would_pay | string | no | would you pay, how much |
- 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 ZenVault 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 | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| create_wakeup | external-sink | external-sink: keyword "webhook" |
| create_schedule | external-sink | external-sink: keyword "webhook" |
| create_deadman | external-sink | external-sink: keyword "webhook" |
| checkin_deadman | no tags | |
| delayed_delivery | no tags | |
| create_drip | sensitive-sourceexternal-sink | sensitive-source: keyword "dump"; external-sink: keyword "webhook" |
| notarize | no tags | |
| attested_fetch | untrusted-input | untrusted-input: keyword "fetch" |
| create_inbox | no tags | |
| collect_messages | no tags | |
| create_frontdoor | no tags | |
| request_approval | external-sink | external-sink: parameter "webhook" |
| check_approval | no tags | |
| notify_human | no tags | |
| guaranteed_delivery | no tags | |
| create_vault | no tags | |
| kv_set | no tags | |
| kv_get | no tags | |
| kv_list | sensitive-source | sensitive-source: keyword "list_keys" |
| save_checkpoint | no tags | |
| create_checkpoint | no tags | |
| load_checkpoint | no tags | |
| store_secret | no tags | |
| create_queue | no tags | |
| queue_push | no tags | |
| queue_lease | no tags | |
| queue_ack | no tags | |
| create_counter | no tags | |
| counter_incr | no tags | |
| claim_operation | no tags | |
| create_idempotency | no tags | |
| publish_page | no tags | |
| create_link | no tags | |
| create_watch | external-sink | external-sink: keyword "webhook", parameter "webhook" |
| watch_status | no tags | |
| create_escalation | no tags | |
| get_resource | no tags | |
| extend_resource | no tags | |
| cancel_resource | no tags | |
| export_resource | no tags | |
| credit_balance | no tags | |
| create_subtoken | no tags | |
| list_prices | no tags | |
| request_feature | 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.
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 1.0.2.
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 ZenVault 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.