Server providing Argo CD integration for MCP clients.
Nothing to run from here
Tailscale 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
22
tools declared
remote
at its publisher
—
calls last 7d
What it does
Read devices, users, keys, ACLs and DNS for a tailnet; manage devices, routes and auth keys.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http usefulapi-tailscale-mcp https://tailscale.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# tailscale_list_devices, tailscale_get_device, tailscale_list_device_routes and 19 more
Tailscale costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 334 servers
usefulapi334 servers
24 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 usefulapi-tailscale-mcp https://tailscale.usefulapi.io/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
22 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 devices in the tailnet (name, addresses, OS, last seen, tags, etc.). Tailscale REST: GET /tailnet/{tailnet}/devices.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fields | string | no | Field set — 'all' returns all fields incl. posture attributes and routes; 'default' is the standard subset. |
Get a single device by id. Tailscale REST: GET /device/{deviceId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
| fields | string | no | Field set — 'all' returns all fields incl. posture attributes and routes; 'default' is the standard subset. |
List the subnet routes a device advertises and which are enabled. Tailscale REST: GET /device/{deviceId}/routes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
List auth keys and API access tokens for the tailnet. Tailscale REST: GET /tailnet/{tailnet}/keys.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| all | boolean | no | If true, returns all keys, tokens and OAuth clients in the tailnet, not just the caller's own (requires appropriate scope). Default false. |
Get details of a single auth key / API access token by id (capabilities, expiry, usage). Tailscale REST: GET /tailnet/{tailnet}/keys/{keyId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyId | string | yes | The key id. |
Get the tailnet's ACL / policy file (returned as JSON via the Accept header, not HuJSON). Tailscale REST: GET /tailnet/{tailnet}/acl.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| details | boolean | no | If true, include metadata about the policy file (e.g. when and by whom it was last updated). |
List the global DNS nameservers configured for the tailnet. Tailscale REST: GET /tailnet/{tailnet}/dns/nameservers.
No parameter schema on file.
Get the tailnet's DNS preferences (e.g. whether MagicDNS is enabled). Tailscale REST: GET /tailnet/{tailnet}/dns/preferences.
No parameter schema on file.
List the DNS search paths (search domains) configured for the tailnet. Tailscale REST: GET /tailnet/{tailnet}/dns/searchpaths.
No parameter schema on file.
Get the tailnet's split-DNS configuration — a map of domain → nameservers. Tailscale REST: GET /tailnet/{tailnet}/dns/split-dns.
No parameter schema on file.
List users of the tailnet, optionally filtered by type, role or status. Tailscale REST: GET /tailnet/{tailnet}/users.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | no | Filter by user type. |
| role | string | no | Filter by role, e.g. owner, admin, member, it-admin, network-admin, billing-admin, auditor. |
| status | string | no | Filter by user status. |
Get a single user by id. Tailscale REST: GET /users/{userId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| userId | string | yes | The user id. |
List the webhook endpoints configured for the tailnet. Tailscale REST: GET /tailnet/{tailnet}/webhooks.
No parameter schema on file.
Get the tailnet's settings (device approval, key expiry, posture, etc.). Tailscale REST: GET /tailnet/{tailnet}/settings.
No parameter schema on file.
Authorize or de-authorize a device (only relevant when device approval is enabled for the tailnet). Tailscale REST: POST /device/{deviceId}/authorized.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
| authorized | boolean | yes | True to authorize the device into the tailnet, false to de-authorize it. |
Set (rename) a device's name. Tailscale REST: POST /device/{deviceId}/name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
| name | string | yes | The new device name. |
Set a device's ACL tags. REPLACES the device's existing tags. Tailscale REST: POST /device/{deviceId}/tags.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
| tags | array | yes | ACL tags to apply, e.g. ["tag:server"]. REPLACES the device's existing tags. |
Expire a device's node key, forcing it to re-authenticate — a security response to a compromised or lost device. Tailscale REST: POST /device/{deviceId}/expire.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
Set the subnet routes ENABLED for a device (from the routes it advertises). REPLACES the enabled set. Tailscale REST: POST /device/{deviceId}/routes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id. |
| routes | array | yes | The set of subnet routes (CIDRs) to ENABLE for this device, e.g. ["10.0.0.0/24"]. REPLACES the enabled set. |
Create a new auth key for the tailnet (used to register new devices). Tailscale REST: POST /tailnet/{tailnet}/keys.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reusable | boolean | no | If true, the key can register multiple devices. |
| ephemeral | boolean | no | If true, devices registered with this key are ephemeral (removed shortly after going offline). |
| preauthorized | boolean | no | If true, devices registered with this key are pre-authorized (skip device approval). |
| tags | array | no | ACL tags to apply to devices created with this key, e.g. ["tag:ci"]. |
| expirySeconds | number | no | Key lifetime in seconds; 0 means no expiry (if allowed by tailnet policy). |
| description | string | no | A short description for the key. |
Delete (revoke) an auth key or API access token by id — a security response. Tailscale REST: DELETE /tailnet/{tailnet}/keys/{keyId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| keyId | string | yes | The key id to delete. |
Delete a device, removing it from the tailnet. Tailscale REST: DELETE /device/{deviceId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| deviceId | string | yes | The device id to delete. |
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 Tailscale 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 1.11.1 · scanned 20 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 · 1 capability
Capabilityhigh
Coveragemanifest
Verificationnot in this report
Surface digestb83e4a1bdeb14fb1a8f25a1f7a65cf120f087ec1e3cc290d4462ede44df2a884
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 |
|---|---|---|
| tailscale_list_devices | no tags | |
| tailscale_get_device | no tags | |
| tailscale_list_device_routes | no tags | |
| tailscale_list_keys | sensitive-source | sensitive-source: keyword "list_keys" |
| tailscale_get_key | no tags | |
| tailscale_get_policy_file | no tags | |
| tailscale_list_dns_nameservers | no tags | |
| tailscale_get_dns_preferences | no tags | |
| tailscale_list_dns_searchpaths | no tags | |
| tailscale_get_split_dns | no tags | |
| tailscale_list_users | no tags | |
| tailscale_get_user | no tags | |
| tailscale_list_webhooks | external-sink | external-sink: keyword "webhook" |
| tailscale_get_tailnet_settings | no tags | |
| tailscale_authorize_device | state-write | state-write: declares destructiveHint: true |
| tailscale_set_device_name | state-write | state-write: declares destructiveHint: true |
| tailscale_set_device_tags | state-write | state-write: declares destructiveHint: true |
| tailscale_expire_device_key | state-write | state-write: declares destructiveHint: true |
| tailscale_set_device_routes | state-write | state-write: declares destructiveHint: true |
| tailscale_create_auth_key | state-write | state-write: declares destructiveHint: true |
| tailscale_delete_key | state-write | state-write: declares destructiveHint: true |
| tailscale_delete_device | state-write | state-write: declares destructiveHint: 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.
tailscale_list_keys → tailscale_list_webhooks
A sensitive-source → external-sink chain exists: tailscale_list_keys → tailscale_list_webhooks.
Supply chain and provenance
Integrityfirst-seen
Surface digestb83e4a1bdeb14fb1
Scanned2026-10-20
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 1.11.1.
1.11.1
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 Tailscale 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.