Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/nekuda-ai/webmcp-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/nekuda-ai/webmcp-kit/plugin)<a href="https://agentmods.dev/plugins/nekuda-ai/webmcp-kit/plugin"><img src="https://agentmods.dev/badge/plugins/nekuda-ai/webmcp-kit/plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/nekuda-ai/webmcp-kit/plugin"><img src="https://agentmods.dev/badge/plugins/nekuda-ai/webmcp-kit/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
webmcp-kit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "webmcp-kit",
"displayName": "WebMCP Kit",
"version": "0.9.0",
"description": "Add WebMCP tools to a web app: read the repo, propose a reviewable tool plan, implement against @nekuda/webmcp-sdk, and verify the tools in a browser — or connect the tools a site already has, without rebuilding them.",
"author": { "name": "nekuda", "url": "https://github.com/nekuda-ai" },
"homepage": "https://github.com/nekuda-ai/webmcp-kit",
"repository": "https://github.com/nekuda-ai/webmcp-kit",
"license": "MIT",
"icon": "./assets/nekuda-logo.svg",
"keywords": ["webmcp", "model-context", "browser-agents", "nekuda", "agent-tools"]
}
What it installs
The manifest is a name and a version. 3 skills, 1 command, 2 hooks travel with it, and installing the plugin installs all of them — 197 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago Changed · +1 lines d358a69b2b1d
- 28d ago Changed b5e54724a3cf
- 29d ago Changed 8671de3b168e
- 1mo ago Changed 8c55d01fff94
- 1mo ago First seen · 13 lines scan A c740f3fe6821
webmcp-kit is a plugin published in the GitHub repository nekuda-ai/webmcp-kit (45 stars, last pushed 17d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
vitaecontext
VitaeContext gives AI agents a private, reusable source of truth about a person's career, then provides focused skills for turning that context into grounded professional work.
mixedbread-skills
Agent skills for search, RAG, parsing, completions, and model harnesses with Mixedbread.
opendeck
Build animated, narrated HTML presentation decks — step-by-step reveals, hover tooltips, a thumbnail rail, fullscreen, and in-browser ElevenLabs voice narration that bakes into a fully offline file.
machine-learning-ops
ML pipeline design, experiment tracking, model evaluation, training debugging, and reproducibility.
apple-dev-skills
Apple, SwiftPM, Xcode, macOS privacy, file access, entitlement, and virtualization workflows.
nib
Original editorial illustrations where a recurring avatar you own performs the idea — seven white-background print looks, a built-in methodology, and an OpenRouter image engine. Turns one idea or a whole article into a consistent illustration set.