io.github.laurells/outflow-mcp
MCP server exposing an Outflow workspace's live architecture graph as context for AI coding agents
التثبيت
أضف هذا إلى إعدادات MCP في عميلك (Claude Desktop: claude_desktop_config.json، وCursor: .cursor/mcp.json، ويستخدم VS Code وغيره الصيغة نفسها «mcpServers»).
outflow-mcpclaude mcp add outflow-mcp -e 'OUTFLOW_BASE_URL=<OUTFLOW_BASE_URL>' -e 'OUTFLOW_API_KEY=<your outflow_api_key>' -e 'OUTFLOW_WORKSPACE_ID=<OUTFLOW_WORKSPACE_ID>' -- npx -y outflow-mcp@0.1.1
{
"mcpServers": {
"outflow-mcp": {
"command": "npx",
"args": [
"-y",
"outflow-mcp@0.1.1"
],
"env": {
"OUTFLOW_BASE_URL": "<OUTFLOW_BASE_URL>",
"OUTFLOW_API_KEY": "<your outflow_api_key>",
"OUTFLOW_WORKSPACE_ID": "<OUTFLOW_WORKSPACE_ID>"
}
}
}
}
متغيرات البيئة
OUTFLOW_BASE_URLBase URL of your running Outflow instance. Defaults to http://localhost:3000 if omitted.OUTFLOW_API_KEYإلزامي سري API key for the workspace to expose. Create one from workspace settings in Outflow (Settings → API Keys) — the raw key (ofk_...) is shown once.OUTFLOW_WORKSPACE_IDإلزامي ID of the workspace to expose. Found in the workspace URL (.../workspace/<id>/...) or workspace settings.
التوثيق
مأخوذ من ملف README للمشروع على GitHub ويُحدَّث أسبوعيًا. تفتح الروابط على GitHub.
المحتويات
outflow-mcp
An MCP (Model Context Protocol) server that exposes a live Outflow architecture graph as context for AI coding agents — Claude Code, Claude Desktop, or any other MCP-compatible client. Lets an agent ask "what does this file depend on", "what breaks if I change this", or "did my last batch of edits introduce a circular dependency" against your workspace's real, currently-live graph.
It's a thin client over Outflow's existing /api/v1 REST API and the
workspace graph routes — no graph logic
is duplicated here.
This package is developed inside the main Outflow monorepo but published from a standalone public mirror: **https://github.com/laurells/outflow-mcp** — that's the repo MCP registries/crawlers point at, and where
npm publishruns from. Changes here get synced there before each release.
Setup
- Create an API key for the workspace you want to expose. In Outflow,
go to workspace settings → API Keys → create one. The raw key (
ofk_...) is shown once — copy it. - Find your workspace ID — it's in the workspace URL
(
.../workspace/<id>/...) or workspace settings. - Build the server:
cd packages/mcp-server npm install npm run build Add it to your MCP client config. For Claude Code, add to your MCP settings (
claude mcp addor the equivalent config file):{ "mcpServers": { "outflow": { "command": "node", "args": ["/absolute/path/to/outflow/packages/mcp-server/dist/index.js"], "env": { "OUTFLOW_BASE_URL": "https://your-outflow-domain.com", "OUTFLOW_API_KEY": "ofk_...", "OUTFLOW_WORKSPACE_ID": "your-workspace-id" } } } }For local development,
OUTFLOW_BASE_URLdefaults tohttp://localhost:3000if omitted.
Tools
| Tool | Use it to ask |
|---|---|
find_node | Is this file tracked? What's its ID? |
list_nodes | What's deprecated / low health / a given type? |
get_dependencies | What does this file rely on? |
get_impact | What breaks if I change this file? (blast radius) |
find_path | How are these two files connected? |
get_architecture_health | What's the overall health grade and at-risk nodes? |
find_architecture_smells | Any circular deps, god nodes, or dead code right now? |
get_architecture_graph | Give me the whole graph at a zoom level. |
get_last_session_recap | What happened in my last coding session? |
All tools that take a path accept a partial match (e.g. "ApiClient" will
match src/ApiClient.ts) — you never need to know Outflow's internal
file::/method:: ID format. An ambiguous partial match returns an error
listing the candidates instead of guessing.
Notes
- This package is standalone — it is never bundled into
server/orweb/, and has no build-time dependency on them. It only talks to a running Outflow instance over HTTP using an API key, so it works equally well pointed at localhost or a deployed instance. get_dependencies/get_impactandfind_architecture_smells/find_pathcall workspace graph routes that (as of this package's introduction) were extended to acceptAuthorization: Bearer ofk_...alongside the existing cookie-session auth — seeserver/src/graph/pathRouter.tsandsmellsRouter.ts.
الأسئلة الشائعة
ما هو io.github.laurells/outflow-mcp؟
MCP server exposing an Outflow workspace's live architecture graph as context for AI coding agents
كيف أثبّت io.github.laurells/outflow-mcp؟
يعمل على جهازك. في Claude Code: claude mcp add outflow-mcp -e 'OUTFLOW_BASE_URL=<OUTFLOW_BASE_URL>' -e 'OUTFLOW_API_KEY=<your outflow_api_key>' -e 'OUTFLOW_WORKSPACE_ID=<OUTFLOW_WORKSPACE_ID>' -- npx -y outflow-mcp@0.1.1. وفي العملاء الآخرين، الصق إعداد JSON من هذه الصفحة في إعدادات MCP الخاصة بهم.
هل يحتاج io.github.laurells/outflow-mcp إلى مفتاح API؟
نعم. يتطلب OUTFLOW_API_KEY, OUTFLOW_WORKSPACE_ID، وتضبطها في إعداداته.
هل io.github.laurells/outflow-mcp مفتوح المصدر؟
شيفرته علنية على GitHub، لكن المستودع لا يعلن ترخيصًا قياسيًا.
من يصون io.github.laurells/outflow-mcp؟
ينشره laurells. يدرجه AI.tn لكنه لا يصونه ولا يوصي به.
من سجل MCP الرسمي. الإدراج ليس توصية: راجع شيفرة الخادم وصلاحياته قبل منحه الوصول إلى بياناتك.