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)
MCP server for Runframe incident management covering incidents, on-call, postmortems, and more.
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。
RUNFRAME_API_KEY, RUNFRAME_API_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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"runframe": {
"command": "npx",
"args": [
"-y",
"@runframe/mcp-server"
],
"env": {
"RUNFRAME_API_KEY": "your-value",
"RUNFRAME_API_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add runframe --env RUNFRAME_API_KEY=your-value --env RUNFRAME_API_URL=your-value -- npx -y @runframe/mcp-server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": {
"runframe": {
"command": "npx",
"args": [
"-y",
"@runframe/mcp-server"
],
"env": {
"RUNFRAME_API_KEY": "your-value",
"RUNFRAME_API_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": {
"runframe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@runframe/mcp-server"
],
"env": {
"RUNFRAME_API_KEY": "your-value",
"RUNFRAME_API_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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
RUNFRAME_API_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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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 GitHub 账户 runframe 验证,该账户拥有此仓库
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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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:RUNFRAME_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.5)于7个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Safe Fetch
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.
MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.
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。
[Runframe](https://runframe.io) is the complete incident lifecycle platform for engineering teams, covering incident response, on-call, and status pages. This MCP server lets you manage those workflows from your IDE or AI agent.
17 tools covering incidents, on-call, services, postmortems, teams, and people lookup. Requires Node.js 20+.
npx, no server to deploy for local useYour IDE / Agent
↓ (stdio or HTTP) MCP Server (this package) ↓ (HTTPS, scoped API key) Runframe API
The server is stateless. It translates MCP tool calls into Runframe API requests, scoped by your API key permissions. No data is stored locally.
Ask your agent:
runframe_acknowledge_incidentrunframe_get_current_oncallrunframe_create_postmortemrunframe_page_someonerunframe_list_incidents with severity filterrunframe_find_userGet your API key from settings inside Runframe.io, then add to your agent:
Claude Code:
claude mcp add runframe -e RUNFRAME_API_KEY=rf_your_key_here -- npx -y @runframe/mcp-server
Cursor (~/.cursor/mcp.json) · VS Code (.vscode/mcp.json) · Claude Desktop (claude_desktop_config.json):
{
"mcpServers": { "runframe": { "command": "npx", "args": ["-y", "@runframe/mcp-server"], "env": { "RUNFRAME_API_KEY": "rf_your_key_here" } } } }
Other MCP clients: Add the JSON config above to your client's MCP config file.
Interactive setup wizard:
npx @runframe/mcp-server --setup
| Variable | Required | Default | Description |
|---|---|---|---|
RUNFRAME_API_KEY | Yes | — | API key (starts with rf_) |
RUNFRAME_API_URL | No | https://runframe.io | API base URL |
MCP_ACCESS_TOKEN | HTTP only | — | Bearer token for HTTP transport. Comma-separated for rotation (new_token,old_token). |
stdio (default) — used by MCP clients like Claude Code and Cursor. No network exposure. This is what the install commands above configure.
Streamable HTTP — for containerized or remote deployments. Requires MCP_ACCESS_TOKEN for bearer auth:
RUNFRAME_API_KEY=rf_... \
MCP_ACCESS_TOKEN=your_token \ npx @runframe/mcp-server --transport http --port 3100 --host 127.0.0.1
Responsibility is split across three boundaries:
RUNFRAME_API_KEY.The server stores nothing. It is a pass-through to the Runframe API.
| Tool | Scopes | Description |
|---|---|---|
runframe_list_incidents | incidents:read | List incidents with filters and pagination |
runframe_get_incident | incidents:read | Get incident by ID or number |
runframe_create_incident | incidents:write | Create an incident |
runframe_update_incident | incidents:write | Update title, description, severity, or assignment |
runframe_change_incident_status | incidents:write | Move to a new status (new, investigating, fixing, monitoring, resolved, closed) |
runframe_acknowledge_incident | incidents:write | Acknowledge (auto-assigns, tracks SLA) |
runframe_add_incident_event | incidents:write | Add a timeline entry |
runframe_escalate_incident | incidents:write | Escalate to the next policy level |
runframe_page_someone | incidents:write | Page a responder via Slack or email |
| Tool | Scopes | Description |
|---|---|---|
runframe_get_current_oncall | oncall:read | Who is on call right now |
| Tool | Scopes | Description |
|---|---|---|
runframe_list_services | services:read | List services |
runframe_get_service | services:read | Get service details |
| Tool | Scopes | Description |
|---|---|---|
runframe_create_postmortem | postmortems:write | Create a postmortem |
runframe_get_postmortem | postmortems:read | Get postmortem for an incident |
| Tool | Scopes | Description |
|---|---|---|
runframe_list_teams | teams:read | List teams |
runframe_get_escalation_policy | oncall:read | Get escalation policy for a severity level |
| Tool | Scopes | Description |
|---|---|---|
runframe_find_user | users:read | Search users by name or email, with optional inactive-user support for historical lookups |
This MCP server follows the public Runframe direct API contract.
service_ids containing public service keys like svc_K7M4Q9TZ2H, not internal UUIDs.runframe_get_service now looks up services by public service_key, not UUID.INC-2026-001 in path parameters.team_name.runframe_create_incident accepts an optional idempotency_key, which is forwarded as the Idempotency-Key header for retry-safe creates.runframe_create_incident defaults severity to SEV2 when omitted, matching the V1 API.title must be 1-200 chars, description maxes at 10000 chars, and service_ids allows at most 50 items.runframe_list_services to discover valid service_key values before creating incidents.runframe_page_someone now uses the latest V1 delivery contract: email, channels, and optional message.incident_number and snake_case nested fields like users_affected, owner_email, and time_to_acknowledge.runframe_find_user to resolve a person name to an email address before filtering incidents by assigned_to or resolved_by.include_inactive=true on runframe_find_user when you need to resolve former employees in historical incident queries.is_active=true or is_active=false on runframe_find_user when you need an explicit V1 active-state filter.runframe_list_teams with search to resolve the exact team_name before filtering incidents.The Docker image runs HTTP transport by default on port 3100:
docker build -t runframe-mcp-server .
docker run -e RUNFRAME_API_KEY=rf_... -e MCP_ACCESS_TOKEN=your_token -p 3100:3100 runframe-mcp-server
HTTP mode is meant for private networks. If you put it on the internet:
MCP_ACCESS_TOKEN regularly. Pass old and new tokens comma-separated for zero-downtime swaps.The Runframe API enforces rate limits server-side. If you hit a limit, tools return a 429 error with a retry hint. For HTTP transport deployments, your reverse proxy can add additional request-level throttling.
MCP_ACCESS_TOKEN accepts comma-separated tokens:
MCP_ACCESS_TOKEN=new_token,old_tokennew_tokenMCP_ACCESS_TOKEN=new_tokenIssues and PRs welcome at github.com/runframe/runframe-mcp-server.