MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
APIFleet 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.
90/100
tool-list score
67
tools declared
remote
at its publisher
—
calls last 7d
What it does
Build and run AI phone agents: provider matrix, call-cost estimates, config checks, call management.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http apifleet-mcp https://apifleet.dev/mcp
# 2 — ask your agent for something these tools do
# apifleet_get_provider_matrix, apifleet_estimate_call_cost, apifleet_check_assistant_config and 64 more
APIFleet costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
APAll 1 server
apifleet1 server
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 apifleet-mcp https://apifleet.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 (Optional workspace key: Bearer <key>) 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
67 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.
Public, no key: discover implemented voice and carrier integrations, setup boundaries, platform pricing and documentation. No provider request or call is made.
No parameter schema on file.
Public, no key: calculate USD platform fees plus caller-supplied blended provider/carrier rates. An estimate, not a provider quote or invoice. Does not place a call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| seconds | integer | yes | — |
| provider_usd_per_minute | number | no | — |
| carrier_usd_per_minute | number | no | — |
Public, no key: seven static configuration checks. Send a redacted configuration without secrets or customer data. No save, credential verification, full API validation or call-quality certification occurs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| config | object | yes | — |
Read the workspace prepaid balance and funding path. Does not start a checkout or call.
No parameter schema on file.
List assistants in the authenticated workspace.
No parameter schema on file.
Get one assistant belonging to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Create a assistant. Saving configuration does not place a call. The REST response includes revision, configuration and attached resource identifiers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Saving configuration does not place a call. The REST response includes revision, configuration and attached resource identifiers. Additional settings are documented in https://apiflee |
Update selected assistant fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Saving configuration does not place a call. The REST response includes revision, configuration and attached resource identifiers. Additional settings are documented in https://apiflee |
| if_revision | integer | no | Optional optimistic concurrency revision, sent as If-Match. Reload after a 409. |
Delete this assistant. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| if_revision | integer | no | Optional optimistic concurrency revision, sent as If-Match. Reload after a 409. |
Replace all attached HTTP tools with existing tools owned by this workspace. Empty tool_ids detaches every tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Attachment set. |
Replace all attached knowledge documents. Each document must belong to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Attachment set. |
Issue a short-lived browser voice-test URL. Opening its WebSocket can incur usage. Never publish the returned token.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Test session options. |
List number bindings. This does not buy phone numbers from a carrier.
No parameter schema on file.
Bind an existing carrier number to a workspace assistant. This changes incoming call routing; configure the carrier webhook separately.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| number | string | yes | International E.164 number, including the leading +. |
| data | object | yes | Number binding. |
Remove the routing binding. This does not release or cancel the carrier number.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| number | string | yes | International E.164 number, including the leading +. |
Read call logs, summary statistics and pagination. Each row may contain transcript, analysis, costs and recording links; recordings require separate authentication.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | Page number; default 1. |
| limit | integer | no | Rows per page; default 200, maximum 1000. |
| search | string | no | Text or call identifier search. |
| assistant_id | string | no | Resource identifier returned by a previous request. |
| source | string | no | Call source filter. |
| model | string | no | Model filter. |
| voice | string | no | Voice filter. |
| outcome | string | no | Outcome filter. |
| sentiment | string | no | Sentiment filter. |
| date_from | string | no | Start date filter. |
| date_to | string | no | End date filter. |
| sort | string | no | Supported sort column; default started_at. |
| order | string | no | — |
Place a real telephone call. Ask the user to approve recipient, caller number and expected usage first. Billing/provider/carrier checks are the same as REST. No automatic retry or universal idempotency guarantee.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Call request. |
| confirm | boolean | yes | Set true only after the user approves this paid action. A timeout is not safe to retry blindly. |
Read recording waveform metadata and available audio channels.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Permanently remove a call recording. The call log remains. Confirm the identifier before deleting.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List http tools in the authenticated workspace.
No parameter schema on file.
Get one tool belonging to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Create a tool. Creating a tool returns its signing secret once. Configuring a tool does not invoke its URL; attached tools can call it during conversations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Creating a tool returns its signing secret once. Configuring a tool does not invoke its URL; attached tools can call it during conversations. Additional settings are documented in htt |
Update selected tool fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Creating a tool returns its signing secret once. Configuring a tool does not invoke its URL; attached tools can call it during conversations. Additional settings are documented in htt |
Delete this tool. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List knowledge in the authenticated workspace.
No parameter schema on file.
Get one knowledge document belonging to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Create a knowledge document. Attach documents separately to use them in an assistant. Total injected knowledge has a 200 KiB limit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Attach documents separately to use them in an assistant. Total injected knowledge has a 200 KiB limit. Additional settings are documented in https://apifleet.dev/docs |
Update selected knowledge document fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Attach documents separately to use them in an assistant. Total injected knowledge has a 200 KiB limit. Additional settings are documented in https://apifleet.dev/docs |
Delete this knowledge document. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List webhooks in the authenticated workspace.
No parameter schema on file.
Create a webhook. Creation returns a signing secret once; verify delivery signatures against the raw body. Events may be retried.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Creation returns a signing secret once; verify delivery signatures against the raw body. Events may be retried. Additional settings are documented in https://apifleet.dev/docs |
Update selected webhook fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Creation returns a signing secret once; verify delivery signatures against the raw body. Events may be retried. Additional settings are documented in https://apifleet.dev/docs |
Delete this webhook. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List simulation personas in the authenticated workspace.
No parameter schema on file.
Get one simulation persona belonging to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Create a simulation persona.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Additional settings are documented in https://apifleet.dev/docs |
Update selected simulation persona fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Additional settings are documented in https://apifleet.dev/docs |
Delete this simulation persona. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List simulation scenarios in the authenticated workspace.
No parameter schema on file.
Get one simulation scenario belonging to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Create a simulation scenario.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Additional settings are documented in https://apifleet.dev/docs |
Update selected simulation scenario fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Additional settings are documented in https://apifleet.dev/docs |
Delete this simulation scenario. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List simulations in the authenticated workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| assistant_id | string | no | Resource identifier returned by a previous request. |
Get one simulation belonging to this workspace.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Create a simulation.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Resource fields. Additional settings are documented in https://apifleet.dev/docs |
Update selected simulation fields. Omitted fields retain their values.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Resource fields. Additional settings are documented in https://apifleet.dev/docs |
Delete this simulation. Review the identifier before deleting; the change cannot be undone.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
List simulation runs and pagination; inspect status before starting another run.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| assistant_id | string | no | Resource identifier returned by a previous request. |
| simulation_id | string | no | Resource identifier returned by a previous request. |
| batch_id | string | no | Resource identifier returned by a previous request. |
| status | string | no | — |
| page | integer | no | Page number. |
| limit | integer | no | Rows per page. |
Read a run, its evaluations and linked call when available.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Delete a completed simulation result. Running runs may reject deletion.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Queue an asynchronous test. Models and speech can incur usage. Approve the run first and poll the returned identifier; do not enqueue again while it is running.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
| data | object | yes | Run options. |
| confirm | boolean | yes | Set true only after the user approves this paid action. A timeout is not safe to retry blindly. |
Queue every simulation for one assistant. This can incur multiple test runs; approve the batch first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Batch options. |
| confirm | boolean | yes | Set true only after the user approves this paid action. A timeout is not safe to retry blindly. |
Read configured voice-cost reference rates. These are not an invoice or a complete call price.
No parameter schema on file.
Read a provider voice catalog using configured server-side credentials. Catalog failure may return an empty list and error; it is not evidence the provider has no voices.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Voice provider identifier. |
Read configured runnable voice presets. Provider catalog requests may reach a vendor.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Optional catalog provider. |
| realtime_provider | string | no | Optional realtime provider. |
| model | string | no | Optional realtime model. |
Read voices compatible with this assistant configuration.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Read supported provider voice settings and validation ranges.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Optional voice provider. |
List which provider credentials are configured. Returns metadata only, never provider secret values.
No parameter schema on file.
List this workspace API-key metadata. Full key values cannot be retrieved.
No parameter schema on file.
Create a new full workspace key. The secret is returned once. Store it privately; never put it in public client code.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| data | object | yes | Key label. |
Revoke a workspace API key immediately. Revoking the key in use disconnects this MCP client on its next request.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Resource identifier returned by a previous request. |
Read available, reserved and total prepaid funds, policy, funding availability and runtime enforcement. Amounts ending in microusd are integer millionths of a USD.
No parameter schema on file.
Read the actual workspace policy. Internal exempt workspaces can differ from the public tariff.
No parameter schema on file.
Read balance activity and pagination cursor. Funding is credited only after verified payment processing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Maximum entries; defaults to 50. |
| before | integer | no | Return entries before this ledger identifier. |
Read confirmed and pending workspace payment records for the configured live/test environment.
No parameter schema on file.
Read the authenticated workspace metrics snapshot. Metrics may reset with the application process and are not a complete billing ledger.
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 APIFleet 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 90 / 100
Release 1.2.0 · scanned 30 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 score90
Findings0 threat · 2 capability
Capabilityhigh
Coveragemanifest
Verificationnot in this report
Surface digesteb5857d804e4610565666e7f83ac257f5bb1034f6a79cef2a94c22b703b904aa
Score vectorthreat 100 → client 90
| 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 |
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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| apifleet_get_provider_matrix | no tags | |
| apifleet_estimate_call_cost | no tags | |
| apifleet_check_assistant_config | no tags | |
| check_entitlements | no tags | |
| list_assistants | no tags | |
| get_assistant | no tags | |
| create_assistant | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| update_assistant | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| delete_assistant | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| set_assistant_tools | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| set_assistant_knowledge | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_browser_test_token | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| list_numbers | no tags | |
| bind_number | external-sinkstate-write | external-sink: keyword "webhook"; state-write: declares readOnlyHint: false |
| unbind_number | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_calls | no tags | |
| create_outbound_call | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| get_waveform | no tags | |
| delete_recording | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_tools | no tags | |
| get_tool | no tags | |
| create_tool | state-write | state-write: declares readOnlyHint: false |
| update_tool | state-write | state-write: declares readOnlyHint: false |
| delete_tool | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_knowledge_documents | no tags | |
| get_knowledge_document | no tags | |
| create_knowledge_document | state-write | state-write: declares readOnlyHint: false |
| update_knowledge_document | state-write | state-write: declares readOnlyHint: false |
| delete_knowledge_document | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_webhooks | no tags | |
| create_webhook | external-sinkstate-write | external-sink: keyword "webhook"; state-write: declares readOnlyHint: false |
| update_webhook | external-sinkstate-write | external-sink: keyword "webhook"; state-write: declares readOnlyHint: false |
| delete_webhook | external-sinkstate-write | external-sink: keyword "webhook"; state-write: declares readOnlyHint: false, destructiveHint: true |
| list_simulation_personas | no tags | |
| get_simulation_persona | no tags | |
| create_simulation_persona | state-write | state-write: declares readOnlyHint: false |
| update_simulation_persona | state-write | state-write: declares readOnlyHint: false |
| delete_simulation_persona | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_simulation_scenarios | no tags | |
| get_simulation_scenario | no tags | |
| create_simulation_scenario | state-write | state-write: declares readOnlyHint: false |
| update_simulation_scenario | state-write | state-write: declares readOnlyHint: false |
| delete_simulation_scenario | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_simulations | no tags | |
| get_simulation | no tags | |
| create_simulation | state-write | state-write: declares readOnlyHint: false |
| update_simulation | state-write | state-write: declares readOnlyHint: false |
| delete_simulation | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| list_simulation_runs | no tags | |
| get_simulation_run | no tags | |
| delete_simulation_run | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| start_simulation_run | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| start_simulation_batch | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| list_tts_rates | sensitive-source | sensitive-source: keyword "read_config" |
| list_tts_voices | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_voice_presets | sensitive-sourceuntrusted-input | sensitive-source: keyword "read_config"; untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_assistant_voice_presets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_tts_settings | no tags | |
| list_provider_credentials | no tags | |
| list_api_keys | no tags | |
| create_api_key | state-write | state-write: declares readOnlyHint: false |
| revoke_api_key | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| get_wallet | no tags | |
| get_billing_policy | no tags | |
| list_balance_activity | no tags | |
| list_payments | no tags | |
| get_metrics | 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.
get_assistant_voice_presets → list_tts_rates → bind_number
A cross-tool exfiltration chain exists: get_assistant_voice_presets → list_tts_rates → bind_number.
Supply chain and provenance
Integrityfirst-seen
Surface digesteb5857d804e46105
Scanned2026-10-30
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 1.2.0.
1.2.0
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 APIFleet 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.