MCP Number Powers Server
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., "@MCP Number Powers ServerCalculate the powers of 5"
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.
MCP Server Sample
A sample repository demonstrating two ways to run an MCP (Model Context Protocol) server using Python or TypeScript: stdio (local subprocess) and HTTP (Python uses HTTP/SSE, TypeScript uses Streamable HTTP).
What It Does
Both servers expose a calculate_powers tool that computes the square, cube, and 4th power of a number. The HTTP server also adds a calculate_negative_powers tool, a numberpowers://info resource containing historical notes about number powers, and a powers_explanation prompt.
Related MCP server: MCP Calculator Streamable HTTP
Project Structure
├── .gitignore
├── LICENSE
├── README.md
├── stdiomcpconfig_opencode.json # opencode config for Python stdio server
├── py/ # Python implementation
│ ├── server.py # Stdio MCP server (single tool)
│ ├── server_http.py # HTTP/SSE MCP server (two tools + resource + prompt)
│ ├── requirements.txt # Python dependencies
│ ├── numberPowers.txt # Text file served as a resource
│ └── opencode.json # opencode config for Python HTTP server
└── ts/ # TypeScript implementation
├── server.ts # Stdio MCP server (single tool)
├── server_http.ts # Streamable HTTP MCP server (two tools + resource + prompt)
├── package.json # Node.js dependencies
├── tsconfig.json # TypeScript configuration
├── numberPowers.txt # Text file served as a resource
└── opencode.json # opencode config for TypeScript HTTP serverPrerequisites
Python 3.10+ (for Python implementation)
Node.js 18+ (for TypeScript implementation)
An MCP-compatible client (e.g., opencode)
Setup
Python
cd py
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtTypeScript
cd ts
npm install
npm run buildRunning the Servers
Python - Stdio Server (py/server.py)
The stdio server runs as a subprocess and communicates over stdin/stdout. It exposes one tool: calculate_powers.
cd py
python server.pyPython - HTTP/SSE Server (py/server_http.py)
The HTTP server runs on http://localhost:8000 and communicates over Server-Sent Events (SSE). It exposes two tools (calculate_powers, calculate_negative_powers), one resource (numberpowers://info), and one prompt (powers_explanation).
cd py
python server_http.pyThe SSE endpoint is available at http://localhost:8000/sse.
TypeScript - Stdio Server (ts/server.ts)
cd ts
npm run startTypeScript - HTTP Server (ts/server_http.ts)
The TypeScript HTTP server runs on http://localhost:8001 and uses the Streamable HTTP transport. It exposes two tools (calculate_powers, calculate_negative_powers), one resource (numberpowers://info), and one prompt (powers_explanation).
cd ts
npm run start:httpThe MCP endpoint is available at http://localhost:8001/mcp.
Adding to opencode
Option 1: Stdio (local subprocess)
Python
The repository includes stdiomcpconfig_opencode.json at the project root with this configuration:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"number-powers": {
"type": "local",
"command": ["python", "py/server.py"],
"enabled": true
}
}
}TypeScript
Add the following to your opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"number-powers": {
"type": "local",
"command": ["node", "ts/dist/server.js"],
"enabled": true
}
}
}Adjust the command array to use absolute paths if needed.
Option 2: HTTP (remote server)
Start the HTTP server first, then add this to your opencode.json:
Python
The repository includes py/opencode.json with this configuration:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"number-powers-http": {
"type": "remote",
"url": "http://localhost:8000/sse",
"enabled": true
}
}
}TypeScript
The repository includes ts/opencode.json with this configuration:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"number-powers-http": {
"type": "remote",
"url": "http://localhost:8001/mcp",
"enabled": true
}
}
}Applying Changes
After saving opencode.json, restart opencode for the MCP server to be available.
Available MCP Capabilities
Server | Type | Tools | Resources | Prompts |
| stdio |
| — | — |
| HTTP/SSE (port 8000) |
|
|
|
| stdio |
| — | — |
| Streamable HTTP (port 8001) |
|
|
|
Tool Details
calculate_powers — Accepts a number, returns its square, cube, and 4th power as a comma-separated string.
calculate_negative_powers — Accepts a number, returns its negative powers (n^-1, n^-2, n^-3) as a comma-separated string. (HTTP server only)
numberpowers://info — Returns historical notes about number powers from ancient civilizations. (HTTP server only)
Prompt Details
powers_explanation — Accepts a number and returns a prompt asking the LLM to calculate and explain all powers of that number (square, cube, 4th power, and negative powers). (HTTP server only)
Invoking Prompts in OpenCode
OpenCode supports invoking MCP prompts through the chat interface. To use the powers_explanation prompt:
Start the HTTP server:
python server_http.pyornpm run start:httpIn OpenCode, mention the prompt in your message, for example:
Use the powers_explanation prompt for number 22OpenCode will call the MCP server's
prompts/getendpoint with the prompt name and arguments.
Alternatively, you can manually invoke the prompt via the MCP protocol:
{
"method": "prompts/get",
"params": {
"name": "powers_explanation",
"arguments": {
"number": 22
}
}
}License
See LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- 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/praseodeveloper/mcpSample'
If you have feedback or need assistance with the MCP directory API, please join our Discord server