Server providing Argo CD integration for MCP clients.
Nothing to run from here
Tethered Task Sessions 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
trust score
8
tools declared
local
runs on your machine
136
downloads
What it does
Tethered connects local AI apps to saved task profiles on your Mac. A session can request power mode, keep-awake, and configured app-priority or suspension policies. Sessions can be ended in Tethered; finite sessions expire automatically. Heat monitoring, alerts, and configured fan protection remain active. Charging policy is independent.
Requirements and pricing
Install Tethered 1.2.0 or later and keep it running on the same Mac and macOS account as your MCP client. Task-profile controls require Tethered Pro and the permissions needed by the selected profile. MCPRush charges nothing for this listing; that does not include a Tethered Pro license.
Setup
1. Install and launch Tethered.
2. Enable AI task sessions in Settings and create a saved task profile.
3. Select your AI app under Manual Setup. Use Open Setup, Export Integration, or Copy Configuration and follow the client-specific instructions. Merge copied settings without replacing existing servers.
4. For direct stdio setup, register the bundled executable: /Applications/Tethered.app/Contents/MacOS/tethered-mcp (adjust for your app location). No adapter compilation or package-registry installation is required.
5. Refresh your MCP client, then ask it to list task profiles and report session status before starting a session.
This is a local macOS integration. Browser-only chats and remote or container-hosted tool processes cannot reach it. Preview integration instructions and client-specific setup: https://github.com/Tumerit-LLC/Tethered/blob/main/Integrations/README.md
Quickstart
There is no one-line install for it here: it is set up the way its own source describes.
Publisher
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Tethered Task Sessions as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
There is no one-line install for it here: it is set up the way its own source describes.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List saved temporary task profiles and duration limits.
No parameter schema on file.
Start one temporary task session using a saved profile for power mode, keep-awake, and optional process priority or suspension policies. The user configures policies and exceptions in Tethered. Automatic modes protect the detected AI client and its descendants; separate model services need exceptions. Suspension does not purge memory. End it when local work finishes; it also expires automatically.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| profile_id | string | yes | — |
| minutes | integer | no | — |
| reason | string | no | — |
Release the specified task session and request normal power policy. Manual changes are preserved.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
Only on an explicit user request to clear all task sessions: end the active session regardless of which chat started it and request normal policy. Takes no arguments. Idempotent when inactive.
No parameter schema on file.
Manual-only global disk-cache purge, solely on an explicit user request. Never automate per prompt or on memory pressure. Includes the AI workload’s disk cache; cannot purge private RAM selectively or save and restore model caches. Returns a pending operation for native confirmation and administrator authorization. Inspect disk_cache_purge in get_session_status before retrying.
No parameter schema on file.
Report intermediate activity for this chat's owned active task. Send tool_started before a call and tool_succeeded or tool_failed afterward; provide stable input text for repetition matching. Send assistant_output, explicit progress, files_changed, or heartbeat as appropriate. Each event needs a new UUID; retry with the same event UUID. Input/output are bounded to 8192 UTF-8 bytes each. Reports ar
| Parameter | Type | Required | Notes |
|---|---|---|---|
| output | string | no | — |
| event_id | string | yes | — |
| kind | string | yes | — |
| input | string | no | — |
| session_id | string | yes | — |
| tool | string | no | — |
Only after the user explicitly chooses to continue or dismiss safeguards for this chat's owned active session: clear warnings and repetition history, reset event/progress timers, and clear pending client pause/cancellation requests. Does not extend the session, change rules, or restart cancelled work.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | string | yes | — |
Get the active task session, expiration, requested controls, and local memory pressure, physical RAM, swap usage, and task safeguard warnings and requested client disposition. Resources are reported even without an active session. Power controls describe requests, not measured hardware state. This tool does not modify processes or reclaim memory.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source is public, though no licence is declared for it
- Runs on your machine — nothing of it reaches our gateway
- 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 Tethered Task Sessions 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: —
ATrust score 93 / 100
Release 0.2.7 · scanned 21 Oct 2026
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
Findings4 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest2dc22d3bf39daa39
Scanned2026-10-21
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
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.2.7.
0.2.7
20 Oct 2026
latestNo release note was published with this version.
0.2.6
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Tethered Task Sessions 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.