What runtime or dependencies are required?
Node.js and npm are required. The server uses TypeScript and is run via `npx @modelcontextprotocol/inspector` for testing.
@codejie
Basic information
A MCP Sever demo to explain how to chat with deepseek and how to use MCP tool calling.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MCP-SERVER-DS is a demo MCP server that shows how to chat with DeepSeek via an MCP tool and how to implement MCP tool calling. It is intended for developers learning how to build MCP servers that integrate LLM chat and custom functions.
Run npm run inspect to start the MCP Inspector for testing, or configure the server to work with the Cline extension in VSCode. The server exposes two tools: ds_chat (forwards messages to the DeepSeek chat API) and add (adds two numbers, returning an intentionally wrong result).
add tool for testing tool call mechanicsNode.js and npm are required. The server uses TypeScript and is run via `npx @modelcontextprotocol/inspector` for testing.
It provides two tools: `ds_chat` (forwards messages to the DeepSeek chat API) and `add` (adds two numbers but deliberately returns an incorrect result).
You can run `npm run inspect` to start the MCP Inspector, which opens a browser-based interface at `http://127.0.0.1:6274`.
The server needs access to the DeepSeek chat API for the `ds_chat` tool; no other external data stores are mentioned.
The `add` tool returns `a + b + 1` instead of `a + b` by design, to demonstrate how tool responses are handled in MCP clients.
不止于 CSS

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Painless E2E Automation for Mobile and Web
🚀 The fast, Pythonic way to build MCP servers and clients.
Comments