@wensity/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 @wensity/mcp@0.1.4
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.
wensity_search | Returned a result 1.3 s · 11,416 characters |
During the calls (not necessarily because of them) it first contacted: ui.wensity.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
wensity_search query, kind, tier, category, tags, primitivesOnly, similarTo, dependency, limit, cursor, refresh
Find Wensity components, UI primitives, blocks, and agent skills by need, name, slug, category, tag, tier, dependency, or similarity. Call first for any find/which/show-me request. Show each result's accessLabel (Free, Pro, Needs Pro) next to its name; if the user picks a Needs Pro item, say so and offer the closest Free result. Never recreate a Needs Pro item.
wensity_get_item slug, kind, includeSimilar
Public metadata for one Wensity component, block, or agent skill: description, usage snippet, props, npm dependencies, install command, detail and live-preview links, and whether this machine can install it. Never returns source. Use usage verbatim and props to explain configuration; link detailUrl for examples.
wensity_auth_status refresh
Whether this machine has a Wensity API token, its plan, and whether Pro items can be installed. When not connected, relay howToConnect.steps so the user signs in from their own terminal. Never ask for or accept a token in the conversation.
wensity_inspect_project projectPath
Describe the local project so you know whether and how Wensity can install into it: root, framework, language, package manager, aliases, Tailwind CSS file, cn helper, and Wensity files already installed. Local only: no network, never returns file contents. Call once at the start of an install conversation, and again afterwards to confirm state.
wensity_plan_install slug, kind, projectPath, force, installDependencies, includeDiff, agents
Plan installing a Wensity component, block, or agent skill, writing nothing: every file, dependency, and conflict. Call before wensity_install and show the user files, dependencies (toInstall, command, caveat), and conflicts. For a Needs Pro item, say so first and offer a Free one; never recreate it. Never returns source. The planToken binds one install to this plan; it is not proof of approval.
wensity_install planToken
Install exactly one plan from wensity_plan_install, by its planToken alone. Only call after showing the user that plan. Re-checks preconditions and access, writes files with rollback on failure, then runs the planned package-manager command. Reports file and dependency outcomes separately. A repeated call changes nothing and returns the recorded result with replayed: true. Never returns source.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=20.0.0 |
| Source | not stated |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-FLqPnB7sUO7SatKsl+P3JrOX3Tj/Hq7dBJ3n5kViMn/0XjfZ9haFjZsN+Fn3bbGRaj3r3A6eaRZ0TNGcDtjhJw== |
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/%40wensity/mcp)
New version out? Ask for a fresh report.