PyModel/dsh-research-plugins--packages-dsh-mcp-context70

dsh-mcp-context7

Context7 MCP 插件:提供最新库文档与代码示例检索

AI 分析

通过 MCP 桥接 Context7 服务,为模型提供最新、特定版本的第三方库文档和代码示例。适合需要编写现代 API 代码的开发者。

包名
dsh-mcp-context7
版本
0.2.0
许可证
MIT
最近更新
2026年8月22日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:PyModel/dsh-research-plugins#34872607e1134dbece3bdb9e4bca92fef1fdf2c6&path:packages/dsh-mcp-context7

dsh-mcp-context7

Context7 MCP for DeepSeek Harness. Connects the Context7 MCP server through the harness's @deepseek-ai/dsh-mcp-client bridge and exposes its tools as mcp__context7__*, giving the model up-to-date, version-specific library documentation and code examples.

Install

dsh plugin --profile web add dsh-mcp-context7
dsh web

Or follow GitHub (latest commit):

dsh plugin --profile web add github:pymodel/dsh-research-plugins#path:packages/dsh-mcp-context7

API key (optional)

Context7 works without a key. For higher rate limits, get a key at context7.com and expose it as an env var or in a .env file:

CONTEXT7_API_KEY=...

The row stays enabled either way; an empty key simply means keyless.

Tools

The model sees the Context7 tools under the context7 namespace (for example mcp__context7__resolve-library-id and mcp__context7__query-docs).

Remove

dsh plugin --profile web remove dsh-mcp-context7

Do not commit real keys. If you already run your own Context7 MCP row, remove it first to avoid a duplicate serverName conflict.