Svelte Agent CoreBLOCK
The official svelte MCP for all your agentic needs.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Repo for the official Svelte MCP server.
Dev setup instructions
pnpm i cp apps/mcp-remote/.env.example apps/mcp-remote/.env pnpm dev
- Set the VOYAGEAPIKEY for embeddings support
[!NOTE] Currently to prevent having a bunch of Timeout logs on vercel we shut down the SSE channel immediately. This means that we can't useserver.logand we are not sendinglist-changednotifications. We can use elicitation and sampling since those are sent on the same stream of the POST request
Local dev tools
MCP inspector
pnpm run inspect
Then visit http://localhost:6274/
- Transport type:
Streamable HTTP - http://localhost:5173/mcp
Database inspector
pnpm run db:studio
https://local.drizzle.studio/
587683a5cef6OBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp -- npx -y @sveltejs/[email protected]
Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Svelte-Doc-Section | read | A single documentation section |
get-documentation | read | Retrieves full documentation content for Svelte 5 or SvelteKit sections. Supports flexible search by title (e.g., |
list-sections | read | Lists all available Svelte 5 and SvelteKit documentation sections in a structured format. Each section includes a |
playground-link-ui | read | UI resource for the Svelte Playground widget |
svelte-autofixer | read | Given a svelte component or module returns a list of suggestions to fix any issues it has. This tool MUST be used whenever the user is asking to write svelte code before sending the code back to the user |
svelte-task | read | Use this Prompt to ask for any svelte related task. It will automatically instruct the LLM on how to best use the autofixer and how to query for documentation pages. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (9 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (10)
exec(`npm view ${package_json.name} version`, (_, version) => {src: 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAGAAAABgCAYAAADimHc4AAAAAXNSR0IB2cksfwAAAAlwSFlzAAALEwAACxMBAJqcGAAACvdJREFUeJztXQuQVMUVHT5GCYmSDwaVMhQWmpSRRIEkJqmdFVQCRuRjCiVq8MMGKKTYGESEREAFhI2i
.cocoignore
.cocominify
.prettierignore
import { base_runes } from '../../constants.js';import { parse } from '../../parse/parse.js';import { walk } from '../../mcp/autofixers/ast/walk.js';import { base_runes } from '../../../constants.js';import type { ParseResult } from '../../../parse/parse.js';Gates applied: no_behavioural_pass.
587683a5cef6full audit observations/trust-audit/mcp-server/sveltejs__svelte-agent-core.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 587683a5cef6 | BLOCK | D | 69 | first audit |
Questions
What is the Svelte Agent Core MCP server?
The official svelte MCP for all your agentic needs.
What tools does Svelte Agent Core expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Svelte Agent Core safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does Svelte Agent Core need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Svelte Agent Core run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as @sveltejs/opencode at 0.1.16.
How current is this page?
The grade is for one exact copy of the source (587683a5cef6), read on 2026-10-06. The repository is watched and re-audited when it changes.