passare-mcp
MCP server for the Passare Public API that enables users to query funeral home case data, including cases, acquaintances, addresses, and contact information, through natural language.
README
Passare MCP
MCP server for the Passare Public API - talk to your funeral-home case data from Claude, Cursor, or any MCP client. First MCP for the Passare platform, MIT-licensed, no vendor relationship required to run.
What you can do with it
Passare is the leading cloud-based funeral home management software in the US. The Public API gives 3rd parties read access to cases (deceased, services, status), acquaintances (next of kin), addresses, and contact info. With this MCP, you can ask:
You: "Show me every case that was updated this week and group them by service status."
Claude: *calls list_updated_cases, summarises*
You: "Pull up the family contacts for case 7f3a1bcd-... and give me phone + email for the next of kin."
Claude: *calls list_case_acquaintances, then get_phone_number and get_email*
You: "Any new cases come in since yesterday?"
Claude: *calls list_new_cases*
Use cases for funeral directors, family-services agencies, and adjacent SaaS:
- Auto-summarise a day's new cases into a daily digest
- Sync case status to a CRM, Google Sheet, or Slack channel
- Pull service addresses into a routing / dispatch tool
- Drive a follow-up call list from next-of-kin phone numbers
Install
pip install -e .
Configure
export PASSARE_API_KEY="<your-bearer-token>"
export PASSARE_ORGANIZATION_ID="<your-organization-uuid>"
Both are issued by Passare after you submit the Public API access form. The org UUID scopes every call to your funeral home.
Who uses this?
- Funeral homes running Passare who want to bring their case data into Claude / Cursor / a custom agent workflow.
- Adjacent SaaS (CRM, dispatch, family-portal, monument companies) building B2B integrations to Passare without waiting on a partner agreement.
- AI engineers prototyping vertical workflows for the deathcare industry.
Use with Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"passare_mcp": {
"command": "passare_mcp",
"env": {
"PASSARE_API_KEY": "your-api-key",
"PASSARE_ORGANIZATION_ID": "your-organization-uuid"
}
}
}
}
Use with Claude Code
claude mcp add passare_mcp -- passare_mcp \
--env PASSARE_API_KEY=your-key \
--env PASSARE_ORGANIZATION_ID=your-uuid
Tools
| Tool | Type | What it does |
|---|---|---|
health_check |
Diagnostic | Verifies credentials by calling the cheapest list endpoint |
list_cases |
Read | List every case in the org (paginated by limit/offset) |
get_case |
Read | Retrieve one case by its Passare UUID |
list_case_acquaintances |
Read | List family / next-of-kin contacts for a case |
list_new_cases |
Read | Incremental sync: cases created since the last poll |
list_updated_cases |
Read | Incremental sync: cases updated since the last poll |
get_address |
Read | Retrieve one address by its Passare UUID |
get_phone_number |
Read | Retrieve a contact's phone by the contact UUID |
get_email |
Read | Retrieve a contact's email by the contact UUID |
Why this exists
The Passare Public API has been live since 2018 and is documented at passare.com/api. The endpoint surface is listed in Cyclr's Passare connector docs: Cases, Address, Contacts. But no first-party MCP server exists, no Zapier / Composio / mcp.so wrapper covers Passare specifically, and the only DIY options are buried in Tribute/Frazer/Passare's funeral-home-lead aggregators (which only surface "what software does this funeral home run?", not actual case data).
This MCP is the missing layer: same auth, same endpoints, no vendor lock-in, MIT-licensed, 9 tools covering the entire read surface of the Public API.
Development
pip install -e ".[dev]"
pytest
ruff check src tests
ruff format --check src tests
mypy src tests
passare_mcp
Architecture
Built on the patterns documented in ~/.mavis/agents/mavis/memory/engineering-playbook.md:
httpx.AsyncClientwith pooling + transport retries- Typed exception hierarchy with structured fields
- Application-level retry with exponential backoff + Retry-After
- Bare
raiseinside@mcp.toolhandlers (FastMCP setsisError=true) - JSONL audit logging per tool call with secret redaction
py.typedmarker;mypy --strictcleanrespx+hypothesisfor unit and property tests
License
MIT.
See also
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。