offload-mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 1 of 1 tool tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y offload-mcp-server@0.4.2
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
1 tool that takes no input and looks read-only was called once with nothing. 1 returned a result.
offload_get_status | Returned a result under 0.1 s · 22 characters |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
offload_submit_task task, steps, output_hint, done_when, context, exclude, paths, workspace, backend, tier, model, reuse, timeout_sec
Hand a heavy READ-ONLY task to a background worker agent (default: agy) and get a job_id back immediately. Use it when the work means reading a lot but the answer is small: scanning many files, filtering large logs, analyzing a big bundle or resource file, inventorying APIs/strings/config across a tree. The worker replies with a short Summary plus Findings with path:line evidence, so you read a few hundred words instead of the files. Do NOT use it for edits, for small lookups you can do in one or two reads, or for anything security-sensitive you must verify line by line yourself. The worker is another model: treat its findings as leads and spot-check the ones you act on. Write a complete BRIEF. The worker executes it literally and does nothing else, so anything you leave vague it will skip or guess: - task: the goal as one concrete question. - steps: ordered, concrete actions; each names what to open or search and what to record. - output_hint: the exact shape of the Findings (columns, grouping, sort order, what goes in each column). - done_when: the stop condition, so the worker neither stops early nor wanders. - context (optional): what you already know (conventions, file roles), so the worker does not rediscover it. - exclude (optional): files, folders or kinds of results to leave out. The worker returns a Step log; the status tells you which steps it did not finish and which in-scope files it never opened. Each job costs the worker a fixed preamble (about 20k tokens for agy) before it reads anything, so do small lookups yourself. A brief identical to a finished job, over unchanged files, returns that job instead of running again (reuse=false to force a new run). Next: call offload_get_status with the job_id and wait_sec=50 until it finishes. To ask the worker more about its report, use offload_followup: it keeps what the worker already read. Example: task="Which HTTP endpoints does api/v1 register, and what auth does each require?" steps=["List every .php file under api/v1 from FILES IN SCOPE.", "In each file, find each route: URL path and the HTTP methods it accepts.", "For each route, record the auth check it calls (function name), or 'none'."] output_hint="table: url | methods | auth check | handler path:line, sorted by url" done_when="Every file under api/v1 has been read and every route is in the table." exclude=["api/v1/tests/"]
offload_followup job_id, message, output_hint, timeout_sec
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 resume a conversation (agy).
offload_get_status job_id, wait_sec, limit
Get the status of one offloaded job, optionally waiting up to 50s 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.
offload_get_result job_id, part, offset, max_chars
Read the worker's report for a finished job, in pages of up to 25000 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).
offload_cancel_task job_id
Stop a queued or running offloaded job and its worker process tree. Finished jobs are left as they are.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=20.3 |
| Source | github.com/tailucanh/offload-mcp-server |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-mZLVYXYsI+nrRrDFZsOdSK6Lgqkk9Li8frwnP2T7YKlW98nS5sZt6vr57nFF7rS3tsi7GufF5inzQTrFB5smag== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/offload-mcp-server)
New version out? Ask for a fresh report.