ShinkaiBLOCK
Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Shinkai
Create Powerful AI Agents using local or remote AIs
Build collaborative AI agents that work together, handle payments, and automate complex workflows
Shinkai is a free, open-source platform that democratizes AI agent creation. No coding required – just drag, drop, and deploy intelligent agents that can work across platforms and handle real-world tasks.
Read this in: 简体中文 | 粵語 | 한국어 | 日本語 | Español
Features • Demo • Examples • Quick Start • Development • Documentation
🚀 Features
**🎯 No-Code Agent Buil
ddaa96e5f6ecOBSERVED · 2026-10-01Connect
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.
claude mcp add source -- npx -y @shinkai/[email protected]
{
"mcpServers": {
"source": {
"command": "npx",
"args": [
"-y",
"@shinkai/[email protected]"
]
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Exo | read | A specialized model platform focused on precise information extraction, efficient summarization, and reliable knowledge retrieval. |
Gemini | read | A state-of-the-art large language model offering advanced reasoning, multimodal capabilities, and extended context handling. |
Groq | read | A hardware-accelerated inference solution optimized for low-latency and high-throughput deployments. |
OpenRouter | read | A scalable orchestration layer that intelligently routes queries across multiple AI models, optimizing performance and cost. |
gpt-oss | read | OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. |
Trust audit
BLOCKgrade F · trust 50/100 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 | WARN |
| 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 (5 observation(s))
- Network
- declared (10 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
const evalCode = new Function('scope', fullCode);return exec(`chmod +x ${path}`);sql-wasm.wasm
icon.icns
newake.otf
embeddings_server_url: Some("http://127.0.0.1:11435".to_string()),nodeAddress: 'http://127.0.0.1:9550',
const ollamaConfig = { host: ollamaApiUrl || 'http://127.0.0.1:11435' };const ollamaConfig = { host: ollamaApiUrl || 'http://127.0.0.1:11435' };const ollamaConfig = { host: 'http://127.0.0.1:11435' };xlinkHref="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAGQAAABkCAYAAABw4pVUAAAACXBIWXMAAAsTAAALEwEAmpwYAAAgAElEQVR4nO28Z3BU19auO2Vpf/eeqlO3bp179rbJYBAIRZQjapFzMs7ggAO2wQhjAybnnEzOOeeMSSZIQiihnFO3Oit
.skill-meta.json
.prettierignore
.taurignore
.babelrc
.babelrc
import baseConfig from '../../eslint.config.mjs';
resources: typeof import('../../libs/shinkai-i18n/src/lib/resources').default;import { useSetJobScope } from '../../components/chat/context/set-job-scope-context';import { useURLQueryParams } from '../../hooks/use-url-query-params';import { treeOptions } from '../../lib/constants';"signature": "dW50cnVzdGVkIGNvbW1lbnQ6IHNpZ25hdHVyZSBmcm9tIHRhdXJpIHNlY3JldCBrZXkKUlVTNG50TktKVkozbXdiZXdua1pvUFVMT0d2M2pwd2g0RlZvck9zTjNNSHZ6TjJsN2ZtaWpnVzAySzFWSXZxckx0TUF6bmRjUHhiMDhsVVo5MTExcnJLR2
const binaryString = atob(fileContentBase64);
const binaryString = atob(fileContentBase64);
const binaryData = Uint8Array.from(atob(response), (c) =>
Gates applied: no_behavioural_pass.
ddaa96e5f6ecfull audit observations/trust-audit/mcp-server/dcspark__shinkai-1.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 |
|---|---|---|---|---|---|
| 2026-10-01 | ddaa96e5f6ec | BLOCK | F | 50 | first audit |
Questions
What is the Shinkai MCP server?
Shinkai is a two click install App that allows you to create Local AI agents in 5 minutes or less using a simple UI. Supports: MCPs, Remote and Local AI, Crypto and Payments.
What tools does Shinkai expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Shinkai safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (50/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Shinkai need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (ddaa96e5f6ec), read on 2026-10-01. The repository is watched and re-audited when it changes.