Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Field operations on a deterministic solver — run jobs, crews & fleet from Claude or ChatGPT.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
CRISPHIVE_API_KEY, CRISPHIVE_BASE_URL标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://api.crisphive.com/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"crisphive": {
"command": "npx",
"args": [
"-y",
"@crisphive/mcp"
],
"env": {
"CRISPHIVE_API_KEY": "your-value",
"CRISPHIVE_BASE_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http crisphive https://api.crisphive.com/mcpclaude mcp add crisphive --env CRISPHIVE_API_KEY=your-value --env CRISPHIVE_BASE_URL=your-value -- npx -y @crisphive/mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"crisphive": {
"url": "https://api.crisphive.com/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"crisphive": {
"command": "npx",
"args": [
"-y",
"@crisphive/mcp"
],
"env": {
"CRISPHIVE_API_KEY": "your-value",
"CRISPHIVE_BASE_URL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"crisphive": {
"type": "http",
"url": "https://api.crisphive.com/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"crisphive": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@crisphive/mcp"
],
"env": {
"CRISPHIVE_API_KEY": "your-value",
"CRISPHIVE_BASE_URL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://api.crisphive.com/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
CRISPHIVE_BASE_URL env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 crisphive.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:CRISPHIVE_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(2.6.0)于19天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Zoo MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
An MCP server that provides access to the Zoo API for various CAD operations and tools.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
The official MCP (Model Context Protocol) server for the Crisphive API — agentic AI scheduling infrastructure for field operations.
Lets AI agents — Claude, ChatGPT, Gemini, Cursor or any MCP client — match schedules between customers and businesses and route crews to jobs by location, skills, and real-time availability: job booking & appointment scheduling, work-order tracking, availability from a live dispatch & scheduling engine, customer (CRM) sync, service catalogs, technician & crew rosters, geographic service territories and fleet — for trades and home services such as HVAC, plumbing, electrical, cleaning, appliance repair and property maintenance. Scheduling is constraint-based on a deterministic solver: the agent handles the conversation, the solver makes the decision — same inputs, same plan, never an LLM guessing at a calendar. Hosted remote server; nothing to install or run (this repository holds the documentation and registry manifest).
https://api.crisphive.com/mcp
Connect (a chsk_test_ sandbox key is enough), then paste any of these straight into your agent:
createCustomer → listJobRequestBookingWindows → createJobRequest → quoteJobRequest → confirmJobRequest)listEmergencyCandidates → previewEmergencyReschedule → commitEmergencyReschedule)listJobRequests → getTechnicianSchedule). Sick call — *"Dmitri called in sick for tomorrow — re-staff his jobs without moving any customer's appointment."* (previewAbsenceResolve → commitAbsenceResolve)
The same prompts appear on every Crisphive listing and docs page, so what you see here is exactly the first-run experience everywhere.
→ Full overview, tool table and one-click connect: https://crisphive.com/claude
Any MCP client that supports remote servers over Streamable HTTP — claude.ai, Claude Desktop, Claude Code, ChatGPT, Gemini CLI, Cursor, VS Code, Windsurf, Cline, Zed, LM Studio, ….
Settings → Connectors → Add custom connector, paste https://api.crisphive.com/mcp. Sign in as the Crisphive business owner when the consent screen opens. *(Custom connectors require a Claude plan that supports them.)*
# OAuth (you'll be prompted to authorize in the browser)
claude mcp add --transport http crisphive https://api.crisphive.com/mcp
claude mcp add --transport http crisphive https://api.crisphive.com/mcp \ --header "Authorization: Bearer chsk_test_YOUR_KEY"
Or add to .cursor/mcp.json:
{
"mcpServers": { "crisphive": { "url": "https://api.crisphive.com/mcp" } } }
code --add-mcp '{"name":"crisphive","url":"https://api.crisphive.com/mcp"}'
Settings → Connectors (developer mode) → add MCP server with URL https://api.crisphive.com/mcp (OAuth).
Add to ~/.gemini/settings.json (note: Gemini CLI uses httpUrl for Streamable HTTP servers):
{
"mcpServers": { "crisphive": { "httpUrl": "https://api.crisphive.com/mcp", "headers": { "Authorization": "Bearer chsk_test_YOUR_KEY" } } } }
Most clients accept the standard remote-server shape:
{
"mcpServers": { "crisphive": { "url": "https://api.crisphive.com/mcp", "headers": { "Authorization": "Bearer chsk_test_YOUR_KEY" } } } }
Only the URL field name varies in a few clients:
| Client | Config file | URL field |
|---|---|---|
| Cline / Roo Code | cline_mcp_settings.json | url |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | serverUrl |
| Gemini CLI | ~/.gemini/settings.json | httpUrl |
| Zed | settings.json → context_servers | url |
Clients that only speak stdio can bridge with mcp-remote:
{
"mcpServers": { "crisphive": { "command": "npx", "args": ["-y", "mcp-remote", "https://api.crisphive.com/mcp"] } } }
@crisphive/mcp)This repository also ships a thin local stdio server: the same 67 tools (same names, same schemas — generated from the same /v1 OpenAPI spec as the hosted endpoint), where each call is an HTTPS request to the Crisphive API with your key. No business logic runs locally.
{
"mcpServers": { "crisphive": { "command": "npx", "args": ["-y", "@crisphive/mcp"], "env": { "CRISPHIVE_API_KEY": "chsk_test_YOUR_KEY" } } } }
Environment variables:
| Variable | Required | Meaning |
|---|---|---|
CRISPHIVE_API_KEY | for tool calls | chsk_live_… = production data, chsk_test_… = isolated sandbox. Create keys in the dashboard (Developers → API keys). |
CRISPHIVE_BASE_URL | no | API origin override (default https://api.crisphive.com). |
Prefer the hosted remote server (https://api.crisphive.com/mcp) when your client supports it — OAuth, no key handling, always current. The local package exists for stdio-only clients and self-hosted setups.
Developing in this repo: npm ci && npm test. The tool registry (src/tools.generated.json) is generated — npm run generate refreshes it from the live spec; CI fails if it drifts from /v1.
Every request is authenticated with a secret API key sent as a bearer token. Create keys from your Crisphive business dashboard. The key prefix selects the data environment:
chsk_live_… → live (production) datachsk_test_… → sandbox (isolated test) dataLoad keys from the environment — never commit them.
Keys expire. The lifetime is chosen when the key is created — 30 days by default, up to 365 — and is fixed for that key's life; it cannot be extended later. To renew, create a *second* key, point your agent at it, then revoke the first: a business can hold several active keys at once, so the changeover has no downtime and needs no special endpoint (the same procedure AWS documents for access keys). Read expires_at from the dashboard or the key API and schedule the swap. An aged-out key fails with API_KEY_EXPIRED, distinct from API_KEY_INVALID, so you can alert on a missed renewal separately from a revocation.
Crisphive emails the business's owners 7 days before a key expires (14 days for an OAuth connection), so an expiry should not be a surprise — but the mail goes to the business, not necessarily to you, so track expires_at yourself. A key deliberately created for less than 7 days gets no advance notice; it would have arrived at creation.
The MCP endpoint additionally supports OAuth 2.1 for end-user connectors (claude.ai, ChatGPT, …): the business owner authorizes your agent on a consent screen and no key is ever handled. A compliant MCP client runs the whole flow automatically — discovery, dynamic client registration, authorization code + PKCE. Full flow, scopes and token lifetimes: docs/integration.md.
67 tools, one per operation of the public /v1 API — same names as the SDK methods (listCustomers, createJobRequest, …), derived from the same OpenAPI spec so REST and MCP never drift. Full reference: docs/tools.md.
| Group | Tools |
|---|---|
| Customers (CRM sync, full CRUD) | listCustomers · createCustomer · getCustomer · updateCustomer · deleteCustomer |
| Bookings (create & track) | createJobRequest · listJobRequests · getJobRequest · getJobRequestTimeline · listJobRequestBookingWindows · listJobRequestChanges |
| Catalog (reads) | listJobTypes · getJobType · listSkills · listSkillCategories · listSkillsByCategory · listServiceAreas · getServiceArea |
| Catalog management (import sync) | createJobType · updateJobType · deleteJobType · createSkillCategory · deleteSkillCategory · createSkill · updateSkill · deleteSkill · createServiceArea · updateServiceArea · deleteServiceArea · createVehicle · updateVehicle · deleteVehicle |
| Team & fleet (reads) | listTechnicians · getTechnician · listVehicles · getVehicle |
| Team roster management (HR-system sync) | listAssignableGroups · createTechnician · updateTechnician · deleteTechnician · replaceTechnicianBuddies · replaceTechnicianLeads · replaceTechnicianVehicles · replaceTechnicianServiceAreas · replaceTechnicianSkills · listTechnicianSkills |
| Matching & scheduling (read-only, engine-computed) | listMatchingSlots · listCrewCandidates · getTechnicianSchedule · listNearbyTechnicians |
| Scheduling actions (drive the schedule) | quoteJobRequest · confirmJobRequest · bookAndConfirmJobRequest · previewJobRequestMove · commitJobRequestMove |
| Priority & emergency dispatch (P0–P3, SLA, cascade) | updateJobPriority · listEmergencyCandidates · previewEmergencyReschedule · commitEmergencyReschedule |
| Absence resolve (sick call — re-staff a technician's whole day) | previewAbsenceResolve · commitAbsenceResolve |
| Technician time off (record a sick day / leave, read existing leave, delete it when they come back) | createTechnicianTimeOff · listTechnicianTimeOff · deleteTechnicianTimeOff |
| Webhooks (REST-hook triggers: subscribe / unsubscribe) | listWebhookEventTypes · createWebhookEndpoint · deleteWebhookEndpoint |
Typical agent flow:
listSkills / listJobTypes → discover reference IDs
createCustomer → { customer_id } listJobRequestBookingWindows → offer only the returned windows createJobRequest → booking created quoteJobRequest → confirmJobRequest → scheduled (auto or forced technician) (quote answers 409 JOB_REQUEST_QUOTE_NOT_SCHEDULABLE when the customer would see no slot — agree a new time, or resend with force: true) getJobRequest / listJobRequestChanges → track status
One-call flow for a phone call or an automation (voice agents: connect to https://api.crisphive.com/mcp?profile=voice for a small tool set):
listCustomers (phone: "+16135550188") → is the caller already a customer?
bookAndConfirmJobRequest → booked + scheduled, or confirmed:false + refusal (the job then waits in the coordinator's queue)
Emergency (P0) flow:
createJobRequest (priority: "p0") → quoteJobRequest
listEmergencyCandidates → ranked techs + crew_recommendation previewEmergencyReschedule → what moves (or reassigns) commitEmergencyReschedule → inserted + auto-confirmed (or preview with an inline job probe, then bookAndConfirmJobRequest with priority p0 + emergency{dispatch: "now"} books and commits in one call)
Sick-call flow (a technician is out — re-
只显示了开头部分;其余内容请在仓库中阅读