Skip to main content

SilverCare Health Profile MCP

SilverCare 健康档案查询 MCP 服务。当前使用模拟数据,仅提供档案查询,不执行健康诊断或风险判断。

工具说明

get_health_profile

根据用户 ID 查询 SilverCare 健康档案。

输入

参数 类型 说明
user_id string 要查询的用户 ID

输出

返回包含 success、user_id、data_source、profile 和 error 字段的字典。data_source 当前固定为 simulated。

三种返回场景:

  1. 查询成功:user_id=user_001 时,success=true,profile 返回模拟档案,error=null。
  2. 档案不存在:其他普通用户 ID 返回 success=false、profile=null,错误码为 PROFILE_NOT_FOUND。
  3. 模拟服务超时:user_id=user_timeout 时返回 success=false、profile=null,错误码为 MCP_TIMEOUT。这是开发阶段的模拟故障,真实部署时应替换为实际的超时和异常处理逻辑。

本地运行

要求 Python 3.10 或更高版本。

使用 pip

pip install -e .
python -m silvercare_mcp

默认通过 stdio 通信。也可以安装依赖后直接运行:

pip install mcp[cli]
python -m silvercare_mcp

如需启动 Streamable HTTP 服务:

MCP_TRANSPORT=streamable-http python -m silvercare_mcp

Windows PowerShell:

$env:MCP_TRANSPORT = "streamable-http"
python -m silvercare_mcp

HTTP 服务默认监听 0.0.0.0:8000,可通过 MCP_HOST 和 MCP_PORT 修改。

使用 uvx

在项目目录运行:

uvx --from . silvercare-mcp

从 GitHub 直接运行:

uvx --from git+https://github.com/wake1103/silvercare-health-profile-mcp.git silvercare-mcp

uvx 默认以 stdio 方式启动。如需 HTTP:

MCP_TRANSPORT=streamable-http uvx --from . silvercare-mcp

AgentArts 接入

AgentArts 是公有云服务,无法访问本地或内网。UVX 方式由平台托管运行;Streamable HTTP 方式必须部署到公网可访问的地址。

方式 A:UVX(推荐)

在 AgentArts 创建 MCP 服务时选择 UVX 安装方式,使用以下配置:

{
  "mcpServers": {
    "silvercare-health": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/wake1103/silvercare-health-profile-mcp.git",
        "silvercare-mcp"
      ]
    }
  }
}

入口默认使用 stdio,适配 UVX 托管调用;无需额外设置 MCP_TRANSPORT。

方式 B:Streamable HTTP(备选)

先将服务部署到公网服务器,并启动:

MCP_TRANSPORT=streamable-http MCP_HOST=0.0.0.0 MCP_PORT=8000 silvercare-mcp

在 AgentArts 中选择 Streamable HTTP 接入方式,填写公网 MCP Endpoint:

https://<YOUR_PUBLIC_DOMAIN>/mcp

请使用 HTTPS,并确认安全组、防火墙和反向代理已开放对应端口及 /mcp 路径。不要把仅监听本机或内网的地址直接填给 AgentArts。

Metadata

Release files for silvercare-health-profile-mcp 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for silvercare-health-profile-mcp 0.1.0
File Size Uploaded Provenance Actions
silvercare_health_profile_mcp-0.1.0.tar.gz 4.1 kB Without provenance Details for silvercare_health_profile_mcp-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for silvercare-health-profile-mcp 0.1.0
File Interpreter ABI Platform Actions
silvercare_health_profile_mcp-0.1.0-py3-none-any.whl Python 3 none any Details for silvercare_health_profile_mcp-0.1.0-py3-none-any.whl

Total release size: 8.9 kB

Release files / silvercare_health_profile_mcp-0.1.0.tar.gz

Download URL silvercare_health_profile_mcp-0.1.0.tar.gz
Size 4.1 kB
Tags Source
SHA-256 checksum
How to use checksums
7df60673610db1a3f6f3e1e00f0890639458d9896a3db6196d37fe80ddb37cda
BLAKE2b-256 checksum
How to use checksums
03f35fab34ce887c19b4a322039f272e001898d2c8f53f0b1d6c436168dbba34
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / silvercare_health_profile_mcp-0.1.0-py3-none-any.whl

Download URL silvercare_health_profile_mcp-0.1.0-py3-none-any.whl
Size 4.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
36f2e2f3740ff18cdd434cb0e2d74fb7382ff1516fcf2fb47adbc9de6b8b3a71
BLAKE2b-256 checksum
How to use checksums
384532b1afeca3d86f84d3b1c20521d13f9595543fbd397e1e93da9b57a103e3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Security for silvercare-health-profile-mcp 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page