开源MCP工具:Secure memory & context optimization 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
SecureContext是开源的MCP工具,用于优化Claude Code的内存和上下文管理,提供安全的替代方案。
开源MCP工具:Secure memory & context optimization 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
SecureContext是开源的MCP工具,用于优化Claude Code的内存和上下文管理,提供安全的替代方案。
开源MCP工具:Secure memory & context optimization 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/iampantherr/SecureContext
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp---secure-memory---context-optimization": {
"command": "npx",
"args": ["-y", "securecontext"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 开源MCP工具:Secure memory & context optimization 执行以下任务... Claude: [自动调用 开源MCP工具:Secure memory & context optimization MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__mcp___secure_memory___context_optimization": {
"command": "npx",
"args": ["-y", "securecontext"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
The security and memory layer for Claude Code. Persistent memory that survives restarts, cryptographic audit trail for every tool call, and the only HMAC-verified admission gate for Anthropic-style filesystem skills. Runs locally on PostgreSQL — zero cloud sync, MIT-licensed.
⚠️ Note on the "SafeSkill 20/100 Blocked" PR comment: that score is a false positive from a regex-based scanner that doesn't understand the difference between defending against a pattern and using it. See SAFESKILL_RESPONSE.md for the line-by-line refutation. The actual project has 786 passing tests including 60+ red-team attack IDs verified against a real threat model.
---
v0.28.0-α (this release) ships the skill spotter dry-run mode — a detector library that mines tool_calls_pg and pretool_events_pg for repeated procedural patterns across sessions. No LLM yet; just structured signals the operator can review on the dashboard. POST /api/v1/skills/spotter/dry-run → see what patterns the agents are repeating.
Upcoming: - v0.28.0-β — LLM-driven spotter agent (Sonnet 4.6 + high-effort extended thinking). Takes the signals, applies the four Anthropic skill-quality gates (procedural-not-factual, clear-trigger, ≥3-repeats, has-progressive-disclosure-leverage), files candidates to skill_candidates_pg for operator review. - v0.28.0-γ — remaining 4 detectors (external script invocation, uncredited high-cost tasks, rejected-mutation clusters, repeated prompt fragments) + optional cron schedule.
---
```bash
git clone https://github.com/iampantherr/SecureContext.git cd SecureContext npm ci
docker compose -f docker/docker-compose.yml up -d
name: hello-world description: Says hello to a name argument. Use whenever the user asks for a greeting.
Run python scripts/hello.py NAME to greet. EOF cat > ~/.claude/skills/hello-world/scripts/hello.py <<'EOF' import sys; print(f"hello {sys.argv[1] if len(sys.argv) > 1 else 'world'}") EOF
mkdir -p ~/.claude/skills/hello-world/scripts
docker compose -f docker/docker-compose.yml restart sc-api curl http://localhost:3099/api/v1/skills/admission-log/verify
SecureContext是一个有潜力的开源MCP工具,提供了优化内存和上下文管理的功能,适用于需要高效内存管理和安全上下文的场景,但需要进一步的测试和评估。
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
经综合评估,开源MCP工具:Secure memory & context optimization 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | SecureContext |
| 原始描述 | 开源MCP工具:Secure memory & context optimization MCP plugin for Claude Code. Drop-in replace。⭐7 · TypeScript |
| Topics | mcpai-agent-memoryclaude-codeclaude-code-plugincontext-managementcontext-mode-alternativetypescript |
| GitHub | https://github.com/iampantherr/SecureContext |
| 语言 | TypeScript |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:未公布 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端