Project Human

io.github.humanity4ai由 GitHub 账号 humanity4ai 发布v1.0.6更新于 Nov 10, 2026

9 humanity skills for AI agents — crisis detection, WCAG 2.2, empathy, cultural sensitivity

发布方自己的服务:TAP

概览

AI 生成的概览

一个本地 MCP 服务器,提供九项“人性化技能”,让助手审查无障碍、文化与认知敏感性,并起草共情或缓和冲突的回复。

可以做什么
  • 按 WCAG 2.2 审查网页合规性,并设置会话的 WCAG 等级
  • 审查内容的认知负荷与简明语言,检查神经多样性友好设计和适老化用户流程
  • 检查消息的文化敏感性,并针对心理健康话题改写文本
  • 生成支持性、非临床的回复并附升级指引,含哀伤支持模式
  • 以共情方式重述消息,并生成结构化的冲突降级方案
适用场景
适合在助手撰写或审阅涉及无障碍、心理健康、哀伤、文化背景或冲突的用户可见内容时使用,希望获得结构化建议和明确的安全边界,而非自由发挥的建议。
运行要求
以 stdio 本地进程运行;README 说明可克隆仓库并用 pnpm 安装,或用 npx 运行 npm 包。未声明账号、API 密钥或环境变量。README 另提到一个远程 Streamable HTTP 端点。
安装前请注意
工具会把用户提供的文本和网页地址发送给服务器分析;README 还列出远程端点,使用它意味着这些内容会离开本机。输出明确为非临床、非法律意见,每条响应都带边界声明,应向用户展示。风险较高时,支持性回复不能替代专业帮助。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Project Human,将其添加到工作区。
  2. 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

@humanity4ai/mcp-servers

[Humanity4AI]

MCP action contracts and server runtime for Humanity4AI skills.

All 9 humanity skills are exposed as standard MCP tools using the official @modelcontextprotocol/sdk JSON-RPC 2.0 protocol, natively compatible with Claude Code, Copilot, Manus AI, OpenCode, LangChain, and any other MCP SDK client.


Quick Start for AI Agents

1. Clone and install

bash
git clone https://github.com/humanity4ai/project_human.gitcd project_humanpnpm install

2. Start the MCP server

bash
pnpm start# or directly:pnpm --filter @humanity4ai/mcp-servers start

The server starts on stdio using the official MCP SDK JSON-RPC 2.0 protocol. All 9 humanity skills are registered as MCP tools and discoverable via tools/list.

A remote endpoint is also available at https://humanity4ai.ascent.partners/api/mcp using Streamable HTTP transport — no clone needed.

3. Configure your MCP client

Local (stdio):

Add to your MCP client configuration (e.g. claude_desktop_config.json, .cursor/mcp.json, opencode.json):

json
{  "mcpServers": {    "humanity4ai": {      "command": "pnpm",      "args": ["--filter", "@humanity4ai/mcp-servers", "start"],      "cwd": "/path/to/project_human"    }  }}

Or use npx once published to npm (no local clone needed):

json
{  "mcpServers": {    "humanity4ai": {      "command": "npx",      "args": ["-y", "@humanity4ai/mcp-servers"]    }  }}

Remote (Streamable HTTP):

json
{  "mcpServers": {    "humanity4ai": {      "url": "https://humanity4ai.ascent.partners/api/mcp"    }  }}

Available Tools (9 skills)

Tool nameSkillDescription
accessibility_auditWCAG Accessibility AuditAudit web pages for WCAG 2.2 compliance (crawl) or set session WCAG level
rewrite_depression_sensitive_contentDepression-Sensitive ContentAudit or rewrite text for mental health sensitivity
supportive_replySupportive ConversationGenerate a supportive, non-clinical reply with escalation guidance; includes grief support modes (presence, practical, reflection)
cognitive_accessibility_auditCognitive AccessibilityAudit content for cognitive load and plain-language compliance
cultural_context_checkCultural SensitivityCheck a message for cultural sensitivity issues
deescalation_planConflict De-escalationGenerate a structured de-escalation plan
empathetic_reframeEmpathetic CommunicationReframe a message with genuine empathy
neurodiversity_design_checkNeurodiversity-Aware DesignAudit UI for ADHD, autism, dyslexia, and sensory sensitivities
age_inclusive_design_checkAge-Inclusive DesignAudit a user flow for age-inclusive design

Protocol

The server uses the official @modelcontextprotocol/sdk and communicates via JSON-RPC 2.0 over two transports:

  • stdio — local process (clone & run, npx, Docker)
  • Streamable HTTP — remote deployment (Vercel, stateless mode)

Tool discovery:

json
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"my-agent","version":"1.0"}}}{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}

Tool invocation:

json
{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"empathetic_reframe","arguments":{"message":"I failed the exam I studied so hard for","tone":"warm"}}}

Safety Boundaries

Every tool response includes a boundaryNotice field. Always surface this to users:

  • accessibility_audit — Compliance guidance only; does not replace legal review
  • rewrite_depression_sensitive_content — Non-clinical UX/content guidance only
  • supportive_reply — Non-clinical support; must escalate when risk is elevated (includes grief support modes)
  • cognitive_accessibility_audit — Design guidance only
  • cultural_context_check — Context-sensitive recommendations with uncertainty disclosure
  • deescalation_plan — No coercive tactics
  • empathetic_reframe — No manipulation or deceptive empathy
  • neurodiversity_design_check — Inclusive design guidance only
  • age_inclusive_design_check — Inclusive design guidance only

Package Use

bash
pnpm add @humanity4ai/mcp-servers# ornpm install @humanity4ai/mcp-servers

Import contracts programmatically:

ts
import { actionContracts, validateContracts } from "@humanity4ai/mcp-servers";const contracts = validateContracts(actionContracts);

Examples

The examples/ directory contains one complete request/response pair per action:

FileAction
examples/accessibility_audit.example.jsonaccessibility_audit
examples/rewrite_depression_sensitive_content.example.jsonrewrite_depression_sensitive_content
examples/supportive_reply.example.jsonsupportive_reply
examples/cognitive_accessibility_audit.example.jsoncognitive_accessibility_audit
examples/cultural_context_check.example.jsoncultural_context_check
examples/deescalation_plan.example.jsondeescalation_plan
examples/empathetic_reframe.example.jsonempathetic_reframe
examples/neurodiversity_design_check.example.jsonneurodiversity_design_check
examples/age_inclusive_design_check.example.jsonage_inclusive_design_check

Roadmap

  • Auth policies and rate controls for remote deployments
  • Telemetry and evaluation hooks
  • Rich scenario scoring beyond structural checks
  • MCP Registry listing (mcp-publisher)

来源:mcp-servers/README.md,提交 f913514

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.6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

其他 Human 集成