MCP Server Healthcare
MCP Server Healthcare
一个用于 NHS 临床编码工作流的 Model Context Protocol (MCP) 服务器 —— 为临床记录建议 ICD-10-CM/OPCS-4/HCC 代码、跟踪 SAR/FOI 信息治理请求、将 DSAR 映射仓库请求运行至分类和临床审查、批量编码,以及通过 Cerner FHIR R4 沙箱读写患者数据。
任何 MCP 客户端(Claude Desktop、Claude Code、Copilot Studio 的 MCP 连接器等)都可以直接调用这些工具 —— 无需 REST API 层。
最初作为 bobbynoble/clinical-coding-bot 的一部分构建;本仓库是独立的 MCP 服务器,包含其封装的业务逻辑的独立副本,因此不依赖该仓库。
工具
领域 | 工具 |
临床编码 |
|
SAR/FOI 追踪器 |
|
DSAR 映射仓库 |
|
批量编码 |
|
Cerner FHIR 沙箱 |
|
cerner_post_condition、cerner_post_procedure 和 cerner_writeback_episode 会对所配置的任何 Cerner 环境执行真实写入(默认为非生产沙箱 —— 参见 app/fhir_cerner.py)。
Related MCP server: LangCare MCP FHIR Server
设置
pip install -r requirements.txt
cp .env.example .env # fill in Azure OpenAI / Search / Cerner credentials as needed无论设置了哪些凭据,所有工具都会加载,但 suggest_clinical_codes 需要配置 Azure OpenAI + Azure AI Search,cerner_* 工具需要 CERNER_CLIENT_ID/CERNER_CLIENT_SECRET —— 在缺少匹配凭据的情况下调用相应工具会以明确的错误失败,而不会导致服务器崩溃。
运行
Stdio(Claude Desktop、Claude Code、大多数本地 MCP 客户端):
python -m MCP_Server_HealthcareClaude Desktop 配置示例(claude_desktop_config.json):
{
"mcpServers": {
"clinical-coding-bot": {
"command": "python",
"args": ["-m", "MCP_Server_Healthcare"],
"cwd": "/absolute/path/to/mcp_server_healthcare"
}
}
}Streamable HTTP(远程访问,例如从 Copilot Studio 或托管的 MCP 客户端):
python -m MCP_Server_Healthcare --transport http --port 8010HTTP 传输需要在 .env 中设置 CODING_API_KEY —— 每个请求都必须携带匹配的 X-API-Key 头,否则会被拒绝并返回 401(默认拒绝)。默认监听 127.0.0.1;设置 MCP_HOST=0.0.0.0(并将其置于 TLS/反向代理之后)即可在 localhost 之外暴露。
仓库结构
MCP_Server_Healthcare/ the MCP server itself (server.py has the tool
definitions; __main__.py the stdio/http entry point;
auth.py the HTTP transport's API-key gate)
app/ business logic each tool wraps — coder.py (RAG
coding), sar_foi.py, dsar.py, batch.py,
fhir_cerner.py. Each stores its state in a SQLite
file created alongside it on first run.备注
阻塞式网络调用(Azure OpenAI/Search、Cerner FHIR)通过
asyncio.to_thread卸载,这样一次慢调用不会阻塞同一服务器上的其他工具调用。SQLite 文件(
app/sar_foi.db、app/batch.db、app/dsar.db)在首次运行时自动创建,并已被 gitignore。
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted MCP server for the Healthie EHR & telehealth API: patients, appointments, charting, tasks.
Hosted MCP for denial, prior auth, reimbursement, workflow validation, batch scoring, and feedback.
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
Privacy-preserving synthetic health data generation. FHIR R4/R5 compliant.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA clean-room SHARP-on-MCP compliant FHIR R4 MCP server that enables AI agents to interact with any FHIR R4 endpoint using SHARP context headers, without server-side OAuth. It provides clinical tools, lab results, imaging, and interactive MCP-UI dashboards.MIT

LangCare MCP FHIR Serverofficial
AlicenseNot gradedqualityDmaintenanceEnterprise-grade MCP Server for FHIR-based EMRs. Enables AI agents to read, search, create, and update any FHIR R4 resource across major EHR systems like EPIC, Cerner, and OpenEMR.283 npm67MIT- AlicenseNot gradedqualityCmaintenanceEnables AI applications to query and retrieve healthcare data (patients, conditions, observations, medications) from a public FHIR R4 server via MCP tools.MIT
- AlicenseAqualityCmaintenanceMCP server for FHIR interoperability, enabling natural language querying and manipulation of clinical data with full CRUD operations, semantic search, and RAG capabilities.13MIT