Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
Nothing to run from here
offload 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
5
tools declared
local
runs on your machine
—
downloads a day
What it does
Hand heavy read-only work to a background agent CLI (Antigravity) and read back a short report.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tailucanh-offload-mcp '--' npx -y offload-mcp-server
# 2 — ask your agent for something these tools do
# offload_submit_task, offload_followup, offload_get_status and 2 more
offload costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TAAll 1 server
tailucanh1 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. This one runs on your machine: your client starts offload 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.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user tailucanh-offload-mcp '--' npx -y offload-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: 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 your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
5 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task | string | yes | The goal: one concrete question the report must answer, e.g. "Which endpoints in api/v1 skip the CSRF check?" |
| steps | array | yes | Ordered actions for the worker, each concrete: what to open or search, what to record. The worker performs exactly these, in order, and logs each as done/partial/not done. |
| output_hint | string | yes | Exact shape of the Findings, e.g. "table: name | path:line | purpose, sorted by path". |
| done_when | string | yes | Stop condition, e.g. "every file under api/v1 is read and every route is listed". |
| context | string | no | Facts you already know that save the worker time: conventions, which file does what, names to look for. |
| exclude | array | no | What to leave out: files, folders, or kinds of results, e.g. ["tests/", "commented-out code"]. |
| paths | array | no | Files or folders to focus on, relative to the workspace, e.g. ["api/core", "dist/app.js"]. Empty = whole workspace. |
| workspace | string | no | Absolute workspace path. Defaults to the current project; other paths must be listed in allowedRoots. |
| backend | string | no | Backend name from the config. Available: …. |
| tier | string | no | Worker model tier, when the backend defines tiers: low for mechanical inventories, medium by default, high for hard reading or a retry after a weak result. |
| model | string | no | Exact worker model id; overrides tier. |
| reuse | boolean | no | Return a finished job with the same brief over unchanged files instead of running again. |
| timeout_sec | integer | no | Kill the worker after this many seconds. Defaults to the backend's timeoutSec. |
Continue a finished job's worker conversation: ask about its report, or answer the question it ended with (an "ASK:" line). The worker keeps what it already read, so this is much cheaper than a new job. Returns a new job_id; collect it with offload_get_status. Works only with backends that can…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | The finished job to continue. |
| message | string | yes | Your question or answer, e.g. "Does api/v1/user/profile.php:26 reject an expired token? Quote the check." |
| output_hint | string | no | Shape of the Findings for this answer. |
| timeout_sec | integer | no | Kill the worker after this many seconds. |
Get the status of one offloaded job, optionally waiting up to …s for it to finish. When the job is done this already includes the worker's Summary, so you usually do not need offload_get_result. Without job_id, lists the most recent jobs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | no | Job ID from offload_submit_task. Omit to list recent jobs. |
| wait_sec | integer | no | Seconds to wait for completion before answering (max …). |
| limit | integer | no | How many recent jobs to list when job_id is omitted. |
Read the worker's report for a finished job, in pages of up to … characters. part="summary" (short answer), "findings" (evidence list), "steps" (Step log: done/partial/not done per step), "uncertain", "full" (whole report), "stderr" (backend error output, for debugging a failed job).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job ID from offload_submit_task. |
| part | string | no | Which part of the report to read. |
| offset | integer | no | Character offset, for paging through long parts. |
| max_chars | integer | no | Maximum characters to return. |
Stop a queued or running offloaded job and its worker process tree. Finished jobs are left as they are.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | Job ID from offload_submit_task. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- 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 offload 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 0.4.0 · scanned 9 Nov 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
Findings5 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digeste2d284f3b8fef8b611b4f891e0dbca10e2f68f9b59ebd16c9cae65bfdabebc96
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 surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, 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 |
|---|---|---|
| offload_submit_task | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| offload_followup | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| offload_get_status | no tags | |
| offload_get_result | no tags | |
| offload_cancel_task | state-write | state-write: declares readOnlyHint: false, 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.
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 digeste2d284f3b8fef8b6
Scanned2026-11-09
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.4.0. Pin a release below and the command asks for exactly that one.
0.4.0
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 offload 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.