
Humane Proxy
io.github.Vishisht16由 GitHub 账号 Vishisht16 发布v0.6.0更新于 Oct 24, 2026
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
概览
一个本地 MCP 服务器,让助手筛查消息中的自残或犯罪意图,并查看会话风险与近期升级事件。
- 可以做什么
- 检查单条消息的安全性,返回自残或犯罪意图检测的类别、分值和触发项,可选按会话跟踪并计算对话中的风险轨迹。查询指定会话累计的风险等级。列出近期被标记的升级事件,供运营人员复核。检测由关键词启发式、可选的语义嵌入和可选的推理大模型三级级联组成。
- 适用场景
- 适用于助手或智能体处理可能涉及自残念头或犯罪意图的用户消息,并希望先做检查、给出关怀回应并通知运营人员的场景。最适合已经运行 Humane Proxy 管道、希望让智能体查询其结果的部署。
- 运行要求
- 作为本地进程运行,从 PyPI 安装并带 mcp 附加项(例如通过 uvx)。推理阶段可选使用 API 密钥:GROQ_API_KEY 用于 LlamaGuard,或 OPENAI_API_KEY 用于 OpenAI 推理。嵌入阶段需要额外安装;基础安装使用 SQLite 存储。
安装
在 SourceWeft 中
- 打开 控制台中的 Humane Proxy,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
Lightweight, plug-and-play AI safety middleware that protects humans.
HumaneProxy sits between your users and any LLM. When someone expresses self-harm ideation or criminal intent, it intercepts the message, alerts you through your preferred channels, and responds with care — before the LLM ever sees it.
[PyPI] [Python] [Downloads] [License] [Tests] [Humane-Proxy MCP server] [MCP Marketplace]
What it does
- Self-harm detected → Blocked with international crisis resources. Operator notified.
- Criminal intent detected → Blocked or flagged. Operator notified.
- Safe → Forwarded to your LLM transparently.
Jailbreaks and prompt injections are deliberately not the concern of this tool — we focus exclusively on protecting human lives.
Quick Start
As a Python library
As an MCP server (Claude Desktop, Cursor, any agent)
This exposes 3 tools to your AI agent: check_message_safety, get_session_risk, and list_recent_escalations.
How it works
Every message runs through up to 3 cascading stages — each catches what the previous one can't, and clear-cut cases exit early:
Stage 2 catches what keywords miss ("Nobody would notice if I disappeared"); Stage 1's reducers keep "how do I kill a process in Linux" from ever being flagged. On top of the per-message pipeline, a per-session risk trajectory with exponential time-decay detects escalation across a conversation and boosts scores on sudden spikes.
Full details: Pipeline documentation.
Benchmarks
Evaluated on two public datasets — SimpleSafetyTests (100 clearly unsafe prompts) for recall, and XSTest (250 safe-but-alarming prompts like "how do I kill a Python process?") for false positives:
Turning on the free reasoning stage lifts recall to 92% at no cost to the false-positive rate. Fully reproducible with the shipped tooling — methodology, machine specs, and per-stage latency in BENCHMARKS.md.
When something is flagged
- Self-harm → the user receives an empathetic response with crisis helplines for 10+ countries (US 988, India iCall/Vandrevala, UK Samaritans, and more) — or your LLM answers with an injected care-context system prompt; your choice.
- Operators are alerted via Slack, Discord, PagerDuty, Teams, or SMTP email — rate-limited per session so a crisis doesn't become alert spam, while every event is still persisted to the audit log.
- Privacy by default — raw message text is never stored, only SHA-256 hashes;
DELETE /admin/sessions/{id}implements the right to erasure end-to-end.
Available On
Installation Extras
Documentation
License
Apache 2.0. See LICENSE.
Copyright 2026 Vishisht Mishra (@Vishisht16). Any attribution is appreciated.
See NOTICE for full attribution information.
Built for a safer world.
来源:README.md,提交 f83368d
工具
0版本历史
1- v0.6.0最新Sep 16, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分