guuey-sdksBLOCK
The @guuey/* packages — CLI, chat kit, scaffolder and SDKs for hosting agents on Guuey
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The open-source surface of guuey — deploy AI agents, their MCP servers, and generative UI from one config file.
This repo is the source of truth published to npm as the @guuey/* scope:
Quick start
npx @guuey/create-agentic-app my-agent cd my-agent && pnpm install pnpm dev # local run: agent + MCP servers guuey login && guuey deploy
Consumer surfaces and the pairing of record
The @guuey/* cohort is published lockstep (one version across all thirteen packag
1761097cca87OBSERVED · 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 worker --env GEMINI_API_KEY=${GEMINI_API_KEY} --env GOOGLE_API_KEY=${GOOGLE_API_KEY} --env GOOGLE_GENAI_API_KEY=${GOOGLE_GENAI_API_KEY} --env GUUEY_API_KEY=${GUUEY_API_KEY} -- npx -y @guuey/[email protected]{
"mcpServers": {
"worker": {
"command": "npx",
"args": [
"-y",
"@guuey/[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}",
"GOOGLE_API_KEY": "${GOOGLE_API_KEY}",
"GOOGLE_GENAI_API_KEY": "${GOOGLE_GENAI_API_KEY}",
"GUUEY_API_KEY": "${GUUEY_API_KEY}"
}
}
}
}Exposed tools (8)
6 read · 1 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 |
|---|---|---|
echo | read | |
roll_dice | read | Roll an N-sided die and return the result. |
todo_create | write | |
todo_delete | destructive | |
todo_list | read | |
todo_toggle | read | |
toggle | read | |
whoami | read | Returns the caller |
Trust audit
BLOCKgrade F · trust 49/100 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 | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
'sk-ant-api03-deadbeefdeadbeef|config agent.test.ts fixture — deadbeef sentinel'
console.log(`Token received: ${maskToken(pasted)}`);console.log(` ${data.token}`);`(ΔL* ${dL.toFixed(1)}, Δab ${dab.toFixed(1)}; needs ΔL* ≥ 6, or a temperature step Δab ≥ 2 with ΔL* ≥ 5). ` +withHeaders({ Authorization: 'Bearer sk-ant-api03-deadbeefdeadbeef' }),const secret = 'guuey_user_super_secret_value_abc4';
token: 'guuey_svc_raw-secret-once',
const SECRET = 'guuey_widget_TESTSECRETTESTSECRETTESTSECRETTESTSECRET';
const SECRET = 'guuey_widget_kQ7ZvN3xLeakCanaryTailAbc123';
token: 'header.payload.signature',
validateNoLiteralSecrets(withHeaders({ 'X-Custom': 'ghp_0123456789abcdefghijklmnopqrstuvwx' })),validateNoLiteralSecrets(withHeaders({ 'X-Slack': 'xoxb-1234567890-abcdefghij' })),validateNoLiteralSecrets(withHeaders({ 'X-Stripe': 'sk_live_0123456789abcdefghij' })),todo_delete
.overlay-remove
expect(from("/pkg/src/sub/deep/c.ts", 'const m = await import("../../fixtures/x.js");')).toEqual(["../../fixtures/x.js"]
const STYLESHEET = readFileSync(new URL("../../styles.css", import.meta.url), "utf8");const css = readFileSync(new URL("../../styles.css", import.meta.url), "utf8");const WIRE_RECONCILE = repoPath('../../../../../backend/libs/cli-wire/reconcile.ts');{...process.env} ... fetch(todo: { kind: 'external', url: 'http://127.0.0.1:6782/mcp', headers: { 'x-static': 'yes' } },url: 'http://127.0.0.1:9111/mcp',
url: 'http://127.0.0.1:9111/mcp',
todo: { url: 'http://127.0.0.1:6782/mcp', transport: 'http', headers: { 'x-static': 'yes' } },Gates applied: critical_finding, no_behavioural_pass.
1761097cca87full audit observations/trust-audit/mcp-server/withguuey__guuey-sdks.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 | 1761097cca87 | BLOCK | F | 49 | first audit |
Questions
What is the @guuey/mcp-apps-host MCP server?
The @guuey/* packages — CLI, chat kit, scaffolder and SDKs for hosting agents on Guuey
What tools does @guuey/mcp-apps-host expose?
8 in total: 6 read-only, 1 that write, and 1 that can delete or overwrite (todo_delete). Every one is listed on this page with its risk.
Is @guuey/mcp-apps-host safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (49/100) 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 @guuey/mcp-apps-host need?
It reads GEMINI_API_KEY, GOOGLE_API_KEY, GOOGLE_GENAI_API_KEY, GUUEY_API_KEY, GUUEY_APP_SECRET and GUUEY_KV_TOKEN 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 @guuey/mcp-apps-host run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @guuey/worker at 0.31.1.
How current is this page?
The grade is for one exact copy of the source (1761097cca87), read on 2026-10-12. The repository is watched and re-audited when it changes.