MCP-X AgentBLOCK
这是一个MCP客户端,让你轻松配置各个大模型,对接各种MCP Server而开发。This is an MCP client that allows you to easily configure various large models and develop interfaces with various MCP servers.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 中文
MCP-X is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨
Use Cases 🎯
AI Agent
MCP-X good at agent and understanding various types of content through its powerful AI agents. Here's an example of food content agent:
Key Features Demonstrated:
- 🍽️ Food Content Analysis: Detailed breakdown of dishes, ingredients, and nutritional information
- 🎯 Targeted Recommendations: Personalized suggestions based on user preferences
- 📊 Structured Output: Well-organized information with clear categorization
- 💬 Interactive Chat: Natural conversation flow with comprehensive responses
Perfect for:
- Food bloggers and content creators
- Nutritionists and health professionals
- Restaurant owners and chefs
- Anyone interested in food analysis and recommendations
This showcases how MCP-X can transform simple queries into detailed, actionable insights across various domains.
What's New
We've just rolled out major updates to improve your experience:
📚 Brand New Knowledge Base Feature (v0.1.0)
MCP-X now supports powerful knowledge base management!
- Knowledge Management: Upload, view, search, and delete knowledge documents (su
4182c52dce3dOBSERVED · 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 scripts --env APPLEIDPASS=${APPLEIDPASS} --env JWT_SECRET=${JWT_SECRET} -- npx -y [email protected]{
"mcpServers": {
"scripts": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"APPLEIDPASS": "${APPLEIDPASS}",
"JWT_SECRET": "${JWT_SECRET}"
}
}
}
}Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
echo | read | A simple echo tool to verify if the MCP server is working properly. It returns a characteristic response containing the input message. |
testServer | read | Test server description |
test_tool | read | A test tool |
tool1 | read | Tool 1 description |
tool2 | read | Tool 2 description |
web_search | read | Web search |
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 | 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 (6 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (14)
rejectUnauthorized: false,
icon.icns
console.log("开始执行openaiModelList函数, apiKey长度:", apiKey?.length || 0)console.log("开始执行anthropicModelList函数, apiKey长度:", apiKey?.length || 0).debug.script.mjs
return crypto.createHash("md5").update(fileBuffer).digest("hex").slice(0, 12);import config from "../../config"
import { MCPClient, WebServer, initDatabase } from "../../services/index.js"import { DatabaseMode, getDB } from "../../services/database/index.js"import { SystemCommandManager } from "../../services/syscmd/index.js"import { MCPServerManager } from "../../services/mcpServer/index.js"return decodeURIComponent(Array.prototype.map.call(atob(str),
@anthropic-ai/sdk, @aws-sdk/client-bedrock, @codemirror/lang-json, @codemirror/lint, @langchain/anthropic, @langchain/aws, @langchain/community, @langchain/core
@modelcontextprotocol/sdk, cors, express
Gates applied: no_behavioural_pass.
4182c52dce3dfull audit observations/trust-audit/mcp-server/timecyber__mcp-x-agent.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 | 4182c52dce3d | BLOCK | D | 69 | first audit |
Questions
What is the MCP-X Agent MCP server?
这是一个MCP客户端,让你轻松配置各个大模型,对接各种MCP Server而开发。This is an MCP client that allows you to easily configure various large models and develop interfaces with various MCP servers.
What tools does MCP-X Agent 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 MCP-X Agent 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 MCP-X Agent need?
It reads APPLEIDPASS and JWT_SECRET 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 MCP-X Agent run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on npm as scripts at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (4182c52dce3d), read on 2026-10-07. The repository is watched and re-audited when it changes.