Borrowing it
Nothing to install: this file belongs to Yuchenhui/mcp-redis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Yuchenhui/mcp-redis/main/CLAUDE.mdgit clone --depth 1 https://github.com/Yuchenhui/mcp-redisWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/yuchenhui/mcp-redis/claude-md)<a href="https://agentmods.dev/instructions/yuchenhui/mcp-redis/claude-md"><img src="https://agentmods.dev/badge/instructions/yuchenhui/mcp-redis/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/yuchenhui/mcp-redis/claude-md"><img src="https://agentmods.dev/badge/instructions/yuchenhui/mcp-redis/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02046 | $0.02046 |
| Opus 5.5 | $0.00818 | $0.00818 |
| Sonnet 5.5 | $0.00409 | $0.00409 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
mcp-redis CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Redis MCP Server - 项目总览
项目愿景
Redis MCP Server 是一个为 AI 智能体应用设计的自然语言接口,旨在通过 MCP (Model Context Protocol) 客户端高效管理和搜索 Redis 数据。它使 AI 驱动的工作流能够与 Redis 中的结构化和非结构化数据进行交互。
架构总览
技术栈
- 语言: Python 3.10+
- 框架: FastMCP (Model Context Protocol)
- 数据库: Redis (支持单实例和集群模式)
- 主要依赖: redis, numpy, click, dotenv
核心架构
- 服务层: 基于 FastMCP 的异步 MCP 服务器
- 连接管理: 单例模式的 Redis 连接管理器,支持 SSL/TLS 和集群
- 工具模块: 按数据类型分组的 Redis 操作工具集
- 配置系统: 灵活的配置管理,支持环境变量和命令行参数
模块结构图
graph TD
A["(根) Redis MCP Server"] --> B["src"];
A --> C["tests"];
B --> D["common"];
B --> E["tools"];
B --> F["main.py"];
B --> G["version.py"];
D --> H["server.py<br/>MCP服务器核心"];
D --> I["config.py<br/>配置管理"];
D --> J["connection.py<br/>Redis连接管理"];
D --> K["logging_utils.py<br/>日志工具"];
E --> L["string.py<br/>字符串操作"];
E --> M["hash.py<br/>哈希操作"];
E --> N["list.py<br/>列表操作"];
E --> O["set.py<br/>集合操作"];
E --> P["sorted_set.py<br/>有序集合操作"];
E --> Q["stream.py<br/>流操作"];
E --> R["json.py<br/>JSON操作"];
E --> S["pub_sub.py<br/>发布订阅"];
E --> T["redis_query_engine.py<br/>向量搜索"];
E --> U["server_management.py<br/>服务器管理"];
E --> V["misc.py<br/>杂项操作"];
E --> AA["redis_execute.py<br/>通用命令工具"];
C --> W["test_*.py<br/>单元测试"];
C --> X["tools/test_*.py<br/>工具测试"];
C --> Y["conftest.py<br/>测试配置"];
click H "./src/common/CLAUDE.md" "查看 common 模块文档"
click L "./src/tools/CLAUDE.md" "查看 tools 模块文档"
click W "./tests/CLAUDE.md" "查看 tests 模块文档"
模块索引
| 模块路径 | 职责描述 | 主要功能 |
|---|---|---|
src/main.py |
应用入口点 | CLI 接口,服务器启动 |
src/common/ |
核心基础设施 | MCP服务器、连接管理、配置、日志 |
src/tools/ |
Redis 操作工具集 | 按数据类型分组的 Redis 操作 |
tests/ |
测试套件 | 单元测试和集成测试 |
运行与开发
安装和运行
# 从 PyPI 安装
pip install redis-mcp-server
redis-mcp-server --url redis://localhost:6379/0
# 开发模式
git clone https://github.com/redis/mcp-redis.git
cd mcp-redis
uv venv
source .venv/bin/activate
uv sync
uv run redis-mcp-server --help
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 220 lines · 2,046 tokens per session scan A af9bdc143c30
mcp-redis CLAUDE.md is an instructions file published in the GitHub repository Yuchenhui/mcp-redis (0 stars, last pushed 1y ago), licensed MIT. It adds 2,046 tokens to every session, about $0.0082 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
mcp-redis CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-redis CLAUDE.mdYuchenhui/mcp-redis | Instructions file | 0 | 1y ago | MIT | A | 2,046 | Claude Code |
| plan-forge caching.instructions.mdsrnichols/plan-forge | Instructions file | 6 | 2d ago | MIT | A | 733 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |