toolbox-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@toolbox-mcpadd 23 and 19"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
toolbox-mcp
A tool-type MCP Server (Tools) demonstrating the complete call chain of "AI Host → MCP Protocol → Multi-language Backend".
Three-layer architecture:
Layer | Language | Responsibility |
Glue (protocol + process bridge) | TypeScript / Node | MCP protocol, tool registration, spawn C++ subprocess |
Kernel (computation) | C++ | Pure computation kernel (e.g., twoSum sum of two numbers) |
Directory Structure
toolbox-mcp
├── src/ TS 胶水层
│ ├── server.ts 主入口(serveStdio + 6 个 register)
│ ├── pathGuard.ts 路径守卫(限制读写 data/)
│ └── tools/ 6 个工具
├── native/ C++ 内核
│ ├── 001.cpp twoSum 源码
│ └── 001.exe 编译产物(不提交,见下)
├── data/ 读写文件工具的操作目录
└── TODO.md 开发计划(#8 Web 面板待办)Related MCP server: MPC-PoC-1-EchoServerToolsbasicas
Environment Requirements
Node.js ≥ 20
MinGW
g++(for compiling the C++ kernel, only needed for thetwo_sumtool)
Installation
npm iCompile the C++ Kernel
native/001.exe is a build artifact and is not committed. You need to compile it yourself after cloning:
g++ -O2 -std=c++20 -static-libgcc -static-libstdc++ native/001.cpp -o native/001.exe-static-libgcc -static-libstdc++ makes the exe bundle its own runtime, avoiding dependency on libstdc++-6.dll.
Running
npm run dev # 开发(tsx watch)
npm start # 运行
npm run typecheck # 类型检查(tsc --noEmit)Tool List
Tool | Description | Layer |
| Echo message | TS |
| Add two numbers | TS |
| Reverse string | TS |
| Read file in | TS |
| Write file in | TS |
| Sum of two numbers (spawn C++ kernel) | TS → C++ |
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceA model-agnostic MCP server exposing example tools (add1, multiply2, greet) for learning purposes, working with any LLM through stdio transport.
- FlicenseNot gradedqualityCmaintenanceA learning-oriented MCP server that exposes basic tools (echo, add, reverse) over stdio transport to validate MCP handshake and tool calls.
- AlicenseAqualityCmaintenanceExposes a verified tool registry (calculator, sandboxed file read, web fetch) over MCP stdio, enabling any MCP-capable client to reuse the same tools from the inspectable ReAct loop.3MIT
- AlicenseNot gradedqualityCmaintenanceWraps Oh My Pi built-in tools (read, write, edit, bash, grep, etc.) as MCP tools, enabling file operations, shell commands, web search, and agent coordination.8Apache 2.0
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
500+ deterministic tools for AI agents: math, conversion, validation, hashing, encoding, date/time.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Blooming-cherry/test_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server