MCP.so
登录
D

Deepseek Fr MCP Server

@rocnubie

基本信息

分类

其他

传输方式

stdio

作者

rocnubie

提交者

Chen Roc

关于 Deepseek Fr MCP Server

暂无概览

Deepseek Fr MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "deepseekfr-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/deepseekfr-mcp/src/index.mjs"
      ]
    }
  }
}

Deepseek Fr MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Deepseek Fr Mcp Server?

A Model Context Protocol server that exposes the canonical DeepSeek FR knowledge surface — models, prompts, chat workflows, pricing, FAQ, and official links — to MCP-compatible AI clients. It is read-only, requires no API keys or quota, and has a ~50 ms cold start. It is intended for French-speaking professionals and developers who want a capable AI assistant without switching to an English-language interface.

How to use Deepseek Fr Mcp Server?

Install via Smithery (npx -y @smithery/cli install deepseekfr-mcp --client claude) or from source (clone repo, pnpm install). Then add the server configuration to your MCP client’s config file (e.g., claude_desktop_config.json or mcp.json). Once connected, use the provided tools (list_models, get_pricing, get_official_links) and resources (site://deepseekfr/models, site://deepseekfr/pricing, site://deepseekfr/faq, site://deepseekfr/links) via the client.

Key features of Deepseek Fr Mcp Server

  • Two model tiers: Pro and Flash, both with 1M token context window
  • Three reasoning modes: Non-think, Think High, Think Max
  • Extended context handling for long documents in a single session
  • API compatibility with OpenAI and Anthropic conventions
  • Benchmark transparency for knowledge, reasoning, code, math, and agents
  • Local execution support with encoding specifications

Use cases of Deepseek Fr Mcp Server

  • Document review: extract summaries from long contracts, compliance docs, or manuals
  • Code assistance: review, debug, or refactor code across common languages
  • Research and reasoning: work through multi-step analytical problems
  • Content drafting: generate French-language copy, reports, or structured documents
  • API prototyping: test DeepSeek model responses before application integration

常见问题

1

What models does Deepseek Fr Mcp Server expose?

It exposes the canonical list of chat models from the DeepSeek FR site, including Pro (deep reasoning, code-heavy) and Flash (faster everyday responses), both with a 1M token context window.

2

Is the server read-only? Does it require an API key?

Yes, the server is read-only and requires no API keys or usage quota.

3

How do I install Deepseek Fr Mcp Server?

You can install via Smithery (`npx -y @smithery/cli install deepseekfr-mcp`) or from source by cloning the repository and running `pnpm install`. Then configure your MCP client’s config file.

4

Which MCP clients are supported?

Claude Desktop, Cursor, Windsurf, and Continue are explicitly mentioned as compatible clients.

5

What resources and prompts are available?

Resources include `site://deepseekfr/models`, `site://deepseekfr/pricing`, `site://deepseekfr/faq`, and `site://deepseekfr/links`. Prompts include `tell_me_about_deepseekfr` and `start_chat_session_deepseekfr`.

评论

其他 分类下的更多 MCP 服务器