LiteCAUTION
Lightweight, composable MCP framework for TypeScript
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Hello and welcome! This folder has been automatically generated by @changesets/cli, a build tool that works with multi-package repos, or single-package repos to help you version and publish your code. You can find the full documentation for it in our repository
We have a quick list of common questions to get you started engaging with this project in our documentation
374270907a21OBSERVED · 2026-10-07Connect
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 starter-mcp-supabase --env ELEVENLABS_API_KEY=${ELEVENLABS_API_KEY} -- npx -y starter-mcp-supabase{
"mcpServers": {
"starter-mcp-supabase": {
"command": "npx",
"args": [
"-y",
"starter-mcp-supabase"
],
"env": {
"ELEVENLABS_API_KEY": "${ELEVENLABS_API_KEY}"
}
}
}
}Exposed tools (92)
89 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Widget | read | Interactive widget for items |
add | write | |
add_item | write | |
analyze | read | Analyze text with specific parameters |
annotatedMessage | read | |
audience | read | Target audience level |
auth-test | read | |
calculate | read | |
calculateSum | read | |
cancel-elicitation | read | |
code | read | Code to review |
collectFormData | read | |
complex-auth-test | read | |
concat | read | |
concept | read | The concept to explain |
confirmAction | read | |
consistency-test | read | |
content | read | Content to analyze |
craft_wonky_prompt | read | |
decline-elicitation | read | |
deleteDatabase | read | |
direct-auth-test | read | |
direct-no-auth-test | read | |
double | read | |
doubleNumber | read | |
dynamic-tool | read | |
dynamicGreet | read | |
echo | read | |
empty-schema-elicitation | read | |
enableDynamicTool | read | |
error-response-elicitation | read | |
error-response-sampling | read | |
errorTool | read | |
experimental-feature | read | |
fetchWebPage | read | |
fileSearch | read | |
focus | read | Analysis focus |
full-elicitation | read | |
full-sampling | read | |
generateId | read | |
getConfig | read | |
getData | read | |
getTinyImage | read | |
getWeather | read | |
greet | read | |
greeting | read | Generate a greeting message |
image-sampling | read | |
includeExamples | read | Include practical examples |
invalid-response-elicitation | read | |
invalid-response-sampling | read | |
invalidOutput | read | |
language | read | Programming language |
length | read | Summary length |
listFiles | read | |
list_items | read | |
longRunningOperation | read | |
middleware-test | read | |
multiply | read | |
myTool | read | |
no-auth-test | read | |
no-elicitation | read | |
no-middleware-auth-test | read | |
no-sampling | read | |
optional-fields-elicitation | read | |
ping | read | |
queryData | read | |
sampling-with-preferences | read | |
search | read | |
sequential-elicitations | read | |
sequential-sampling | read | |
setConfig | read | |
severity | read | Review severity |
simpleEcho | read | |
slow-tool | read | |
strictness | read | Review strictness level |
style | read | Documentation style |
sum | read | |
summarize | write | Create a summary prompt |
test | read | |
test-capabilities | read | |
test-tool | read | |
text | read | Text to summarize |
text_to_speech | read | |
timeout-elicitation | read | |
timeout-sampling | read | |
tool-with-metadata | read | |
tool-without-metadata | read | |
topic | read | Research topic |
unvalidated | read | |
validated | read | Prompt with runtime validation |
with-elicitation | read | |
with-sampling | read |
Trust audit
CAUTIONgrade B · trust 80/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (22)
curl -i --location --request POST 'http://127.0.0.1:54321/functions/v1/mcp-server/mcp' \
curl 'http://127.0.0.1:54321/functions/v1/mcp-server/health'
token: "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.test",
.dev.vars.example
CLAUDE.md
README.md
exec(input?: (string | URLPatternInit), baseURL?: string): URLPatternResult | null;
exec(query: string): Promise<D1ExecResult>;
import type { AuthInfo } from "../../src/auth.js";import { McpServer, StreamableHttpTransport } from "../../src/index.js";import type { MCPServerContext } from "../../src/types.js";} from "../../src/index.js";
import { InMemoryClientRequestAdapter } from "../../src/index.js";curl 'http://127.0.0.1:54321/functions/v1/mcp-server/health'
atob(data: string): string;
declare function atob(data: string): string;
const decoded = atob(args.value);
@clerk/backend, @clerk/mcp-tools, @valibot/to-json-schema, hono, valibot, wrangler
@valibot/to-json-schema, hono, valibot, wrangler
hono, typescript
fastify, zod, @types/node, tsx, typescript
arktype, hono, typescript
Gates applied: no_behavioural_pass.
374270907a21full audit observations/trust-audit/mcp-server/fiberplane__lite.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 374270907a21 | CAUTION | B | 80 | first audit |
Questions
What is the Lite MCP server?
Lightweight, composable MCP framework for TypeScript
What tools does Lite expose?
92 in total: 89 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Lite safe to connect to an agent?
With care. The audit graded it B (80/100) and found 22 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Lite need?
It reads ELEVENLABS_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 Lite run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as starter-mcp-supabase.
How current is this page?
The grade is for one exact copy of the source (374270907a21), read on 2026-10-07. The repository is watched and re-audited when it changes.