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/khromov/svelte-llm-mcpWrote 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/mcp/khromov/svelte-llm-mcp/svelte-llm-local)<a href="https://agentmods.dev/mcp/khromov/svelte-llm-mcp/svelte-llm-local"><img src="https://agentmods.dev/badge/mcp/khromov/svelte-llm-mcp/svelte-llm-local/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/mcp/khromov/svelte-llm-mcp/svelte-llm-local"><img src="https://agentmods.dev/badge/mcp/khromov/svelte-llm-mcp/svelte-llm-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
svelte-llm-local 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 11d 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
{
"svelte-llm-local": {
"type": "sse",
"url": "http://localhost:5173/mcp/sse"
}
}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.
- 11d ago First seen · 6 lines scan A 9cd073271a60
svelte-llm-local is an MCP server published in the GitHub repository khromov/svelte-llm-mcp (159 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other mcp servers, from other repositories
svelte
MCP server "svelte", hosted remotely at mcp.svelte.dev, as configured in oekazuma/svelte-vitals.
nuxt-ui-remote
MCP server "nuxt-ui-remote", hosted remotely at ui.nuxt.com, as configured in fmilioni/agents-board.
skeleton-svelte-mcp
MCP server "skeleton-svelte-mcp" as configured in mxmauro/mcp-skeleton-dev. Runs locally from the skeleton-svelte-mcp npm package.
svelte
MCP server "svelte", hosted remotely at mcp.svelte.dev, as configured in wesselgrift/sveltekit-spa.
figma-dev-tools
Figma Dev Tools MCP Server v1.4.13 - Bridge Figma designs to code with AI-powered token extraction, framework-agnostic structured data, React/Vue/HTML component generation, asset downloads, XSS security protection, smart hierarchy fixing, SVG inline rende. Runs locally from the figma-dev-tools npm package.
local-component-mcp
AST-powered MCP server for Vue/React component analysis — eliminates AI hallucinations on local business components. Runs locally from the @wllcyg001/local-component-mcp npm package.