json-renderBLOCK
The Generative UI framework
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The Generative UI framework.
Generate dynamic, personalized UIs from prompts without sacrificing reliability. Predefined components and actions for safe, predictable output.
# for React npm install @json-render/core @json-render/react # for React with pre-built shadcn/ui components npm install @json-render/shadcn # or for React Native npm install @json-render/core @json-render/react-native # or for video npm install @json-render/core @json-render/remotion # or for PDF documents npm install @json-render/core @json-render/react-pdf # or for HTML email npm install @json-render/core @json-render/react-email @react-email/components @react-email/render # or for Vue npm install @json-render/core @json-render/vue # or for Svelte npm install @json-render/core @json-render/svelte # or for SolidJS npm install @json-render/core @json-render/solid # or for terminal UIs npm install @json-render/core @json-render/ink ink react # or for full Next.js apps (routes, layouts, SSR, metadata) npm install @json-render/core @json-render
24dd162ef470OBSERVED · 2026-10-12Connect
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 e2e-tests --env AI_GATEWAY_API_KEY=${AI_GATEWAY_API_KEY} --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env ELEVENLABS_API_KEY=${ELEVENLABS_API_KEY} --env JEV_AI_GATEWAY_API_KEY=${JEV_AI_GATEWAY_API_KEY} -- npx -y e2e-tests{
"mcpServers": {
"e2e-tests": {
"command": "npx",
"args": [
"-y",
"e2e-tests"
],
"env": {
"AI_GATEWAY_API_KEY": "${AI_GATEWAY_API_KEY}",
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"ELEVENLABS_API_KEY": "${ELEVENLABS_API_KEY}",
"JEV_AI_GATEWAY_API_KEY": "${JEV_AI_GATEWAY_API_KEY}"
}
}
}
}Exposed tools (16)
13 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
Bicycle | read | A bicycle scene captured with gaussian splatting |
Bonsai | read | A bonsai tree captured with gaussian splatting |
Confetti | read | A button that fires confetti when clicked |
Garden | read | A garden scene captured with gaussian splatting |
Grass | read | Large grass plane |
Kitchen | read | An indoor kitchen scan showing spatial depth and lighting |
Mystify | read | Neon wireframe torus knots orbiting in the void -- the Windows Mystify screensaver in 3D |
Pipes | read | Classic 3D Pipes screensaver -- chrome pipes snaking through space at right angles |
Player | read | Default player |
Starfield | read | Classic Windows starfield screensaver -- flying through stars at warp speed |
Stump | read | A tree stump with organic textures and natural detail |
navigate | read | Navigate to a route within the app. Params: { href: string } |
pushState | read | Append an item to an array in state. Params: { statePath: string, value: any, clearStatePath?: string }. Value can contain { |
removeState | destructive | Remove an item from an array in state by index. Params: { statePath: string, index: number } |
setState | write | Update local state |
validateForm | write | Validate all registered form fields and write the result to state. Params: { statePath?: string }. Defaults to /formValidation. Result: { valid: boolean, errors: Record<string, string[]> }. |
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 | WARN |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (15)
style: 'mapbox://styles/mapbox/standard',
const url = `http://127.0.0.1:${port}`;removeState
.node-version
import { catalog, customRules } from "../../lib/render/catalog";import { stripe, formatAmount, formatDate } from "../../stripe";import { stripe, formatAmount, formatDate } from "../../stripe";import { schema as imageSchema } from "../../image/src/schema";import { schema as inkSchema } from "../../ink/src/schema";@ai-sdk/gateway, @mdx-js/mdx, @radix-ui/react-dialog, @radix-ui/react-slot, @radix-ui/react-tabs, @upstash/ratelimit, @upstash/redis, @vercel/analytics
@ai-sdk/gateway, @ai-sdk/react, @react-three/drei, @react-three/fiber, @streamdown/code, ai, class-variance-authority, clsx
@ai-sdk/gateway, ai, class-variance-authority, clsx, drizzle-orm, lucide-react, next-themes, postgres
@ai-sdk/gateway, @ai-sdk/react, ai, next, react, react-dom, @types/node, @types/react
@ai-sdk/gateway, @react-three/drei, @react-three/fiber, @react-three/postprocessing, @react-three/rapier, @upstash/ratelimit, @upstash/redis, @vercel/blob
pnpm-lock.yaml
Gates applied: no_behavioural_pass.
24dd162ef470full audit observations/trust-audit/mcp-server/vercel-labs__json-render.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 |
|---|---|---|---|---|---|
| 2026-10-12 | 24dd162ef470 | BLOCK | D | 69 | first audit |
Questions
What is the @json-render/mcp MCP server?
The Generative UI framework
What tools does @json-render/mcp expose?
16 in total: 13 read-only, 2 that write, and 1 that can delete or overwrite (removeState). Every one is listed on this page with its risk.
Is @json-render/mcp 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. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does @json-render/mcp need?
It reads AI_GATEWAY_API_KEY, ANTHROPIC_API_KEY, ELEVENLABS_API_KEY, JEV_AI_GATEWAY_API_KEY, KV_REST_API_TOKEN and OPENAI_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 @json-render/mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as e2e-tests.
How current is this page?
The grade is for one exact copy of the source (24dd162ef470), read on 2026-10-12. The repository is watched and re-audited when it changes.