@archestack/mcp
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 @archestack/mcp@0.3.1
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.
search_projects | Returned a result 0.5 s · 5,313 characters |
During the calls (not necessarily because of them) it first contacted: archestack.com.
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
search_projects query, list, category, license, no_gpu, arm64, has_demo, limit
Find open-source AI projects across both Archestack lists by words and filters. Words match names, repos, taglines, categories and the products a project replaces; results rank by how many words match, then exact names, then projects whose name or category holds the words, then by score. Put hard needs in the filters, not the words (no_gpu instead of "without a GPU"). Use it when the user describes a need rather than naming a project; for a ranking of one category use top_in_category, for replacements of a named paid product use alternatives_to.
get_project project
Everything Archestack has on one project: score and the parts it is made of, place in its category, GitHub facts (stars, license, last commit and release, language, Docker, arm64, GPU, RAM, external services, port), project health, demo and docs links, and the review (summary, audience, strengths, weaknesses). Use it when the user names one project and wants the full picture; for only what it takes to install it use deploy_facts, for two or more projects use compare.
deploy_facts project
The facts an agent needs before installing or deploying one project: Docker files, arm64 build, GPU need, minimum RAM, outside services it needs, web port, what its README says it needs, docs and demo links, and upkeep (latest release, releases in 12 months, security advisories, its package). null means Archestack does not know. Archestack does not track hosting cost or deploy templates. Use it right before installing or self-hosting a project; for its score and review use get_project.
top_in_category category, list, limit
The ranking of one category, best first, with score and tagline. An unknown category returns the list of categories, so calling it with a guess is a cheap way to learn the category ids. Use it for "what is the best X"; to filter by GPU, arm64 or license, or to search across categories, use search_projects.
compare projects
Put 2 to 4 projects side by side: score and its parts, place, stars, license, last commit, Docker, arm64, GPU, RAM, external services, strengths and weaknesses. Use it when the user is choosing between named projects ("X or Y"); with only one name, find candidates first with top_in_category or alternatives_to.check_repo repo
Check a GitHub repo before installing it, most useful for an MCP server, skill or plugin: whether Archestack lists it, its license in plain words, upkeep, the safety checks it passed (with the failed ones and their evidence) and up to 3 higher-ranked projects in its category. "Checks passed" means those checks passed, not that the code is safe. A repo Archestack does not list returns listed: false and a link to suggest it. Use it when the user pastes a GitHub link they plan to install or run; for a project they name without a link use get_project.
alternatives_to product
Open-source projects that replace a paid or closed product (e.g. Cursor, ChatGPT, Notion), highest score first. own_claim is true when the project says so in its own README. Use it when the user names a product and asks what can replace it or how to self-host it instead; to weigh the picks against each other, pass them to compare.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=22 |
| Source | github.com/archestack/mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-ak3VRzEh23yvkQ0R8+jHCKb854oIKsa9TUg1GrUvAS4kKJlwJ87O/frKR47UjzZ9s9FYZ1pmLA5rNtJWZlXJSQ== |
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/%40archestack/mcp)
New version out? Ask for a fresh report.