Calculate MCP
Enables LLMs to perform basic calculations using a calculator interface.
Calculate MCP
A Model Context Protocol (MCP) server that provides browser automation capabilities using basic calculator feature. This server enables LLMs to interact with calculator. (I actually made it for a test program)
Use Cases
- The test code for to connect MCP feature.
- The toy projects
Example config
{
"mcpServers": {
"calculate": {
"command": "npx",
"args": [
"-y",
"@wrtnlabs/calculator-mcp@latest"
]
}
}
}
Installation in VS Code
Alternatively, you can install the Playwright MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"calculator","command":"npx","args":["-y", "@wrtnlabs/calculator-mcp@latest"]}'
# For VS Code Insiders
code-insiders --add-mcp '{"name":"calculator","command":"npx","args":["-y", "@wrtnlabs/calculator-mcp@latest"]}'
After installation, the Calculator MCP server will be available for use with your GitHub Copilot agent in VS Code.
CLI Options
The Calculator MCP server supports the following command-line options:
--port <port>: Port to listen on for SSE transport
Running headed browser on Linux w/o DISPLAY
When running headed browser on system w/o display or from worker processes of the IDEs,
run the MCP server from environment with the DISPLAY and pass the --port flag to enable SSE transport.
npx @wrtnlabs/calculator-mcp@latest --port 8931
And then in MCP client config, set the url to the SSE endpoint:
{
"mcpServers": {
"calculator": {
"url": "http://localhost:8931/sse"
}
}
}
Programmatic usage with custom transports
import { createServer } from "@wrtnlabs/calculator-mcp";
// ... other import statement
const client = new Client({
name: "test client",
version: "0.1.0",
});
const server = createServer({
name: "calculator",
version: "1.0.0"
});
const [clientTransport, serverTransport] = InMemoryTransport.createLinkedPair();
await Promise.all([
client.connect(clientTransport),
server.connect(serverTransport),
]);
Tools
- add
- sub
- mul
- div
- mod
- sqrt
관련 서버
Kone.vc
스폰서Monetize your AI agent with contextual product recommendations
Carryo
Carryo is a remote MCP server for sharing Claude or ChatGPT-created HTML artifacts as live links.
legends-mcp
Chat with legendary founders & investors via MCP. 36 AI personas including Elon Musk, Warren Buffett, Steve Jobs, CZ, and more. No API key required - Claude does the roleplay!
LynxPrompt MCP
Browse, search, and manage AI configuration blueprints and prompt hierarchies via LynxPrompt
Out to Lunch
Daily world briefing that tells AI assistants what's actually happening right now. Leaders, conflicts, deaths, economic data, holidays. Updated daily so they stop getting current events wrong.
Little Irons
Manage your job search directly. List jobs, create applications, add events, run company research, generate templates, and more.
GistPad MCP
Manage and share personal knowledge, daily notes, and reusable prompts using GitHub Gists.
Feishu/Lark OpenAPI
Connects AI agents to the Feishu/Lark platform to automate document processing, conversation management, and calendar scheduling via its OpenAPI.
PM Copilot
Triangulates customer support tickets and feature requests to generate prioritized product plans with convergence scoring and PII scrubbing.
Kit.com (formerly ConvertKit) MCP
Manage your email lists, subscribers, broadcasts, sequences, and more through natural language.
YNAB
Access and manage your YNAB (You Need A Budget) data through MCP-enabled clients.