artifactgraph
Enables local-first analysis of platform specifications against registries, identifying gaps and generating allowlisted code for Cursor and CLI workflows.
README
artifactgraph
Local MCP for platform-bases: analyze specs/bullets vs registries, needs-* gaps, grill confirms, allowlisted codegen — cloud only gets a small cloudPromptSlice.
- GitHub: raintr91/artifactgraph
- Design: docs/ARCHITECTURE.md
- Install (Win/WSL): docs/INSTALL.md
- Local-first flow: docs/INTERNALS.md
- Parity (legacy drift): docs/PARITY.md
- Cursor examples: examples/cursor/ (rule + skill + phase hooks)
Quick install (like CodeGraph)
Linux / WSL
curl -fsSL https://raw.githubusercontent.com/raintr91/artifactgraph/main/install.sh | bash
artifactgraph version
artifactgraph install --target=cursor --yes
Windows (PowerShell) — prefers WSL if present
irm https://raw.githubusercontent.com/raintr91/artifactgraph/main/install.ps1 | iex
npx
npx --yes github:raintr91/artifactgraph
Requires Node ≥ 22 (uses node:sqlite).
What it does (local-first)
| Step | CLI / MCP tool |
|---|---|
| Map bases | artifactgraph projects / artifactgraph_projects |
| Wire Cursor | artifactgraph install --target=cursor |
| Wire product | artifactgraph init → artifactgraph.json |
| Index registries | artifactgraph rebuild |
| Preflight | analyze / gaps / grill_check / parity_check |
| Gen allowlist | gen --command registryValidate |
CLI cheat sheet
artifactgraph version
artifactgraph install --target=cursor --yes
artifactgraph projects
cd ~/workspace/portal
artifactgraph init
artifactgraph rebuild
artifactgraph analyze --bullets "list hotels with status chip"
artifactgraph parity --findings examples/parity/sample-findings.yaml
artifactgraph gen --command registryValidate
Env: ARTIFACTGRAPH_WORKSPACE = folder containing portal/, nextjs/, …
Source map (for learning / next MCP)
| Path | Meaning |
|---|---|
install.sh / install.ps1 |
curl / irm entrypoints |
bin/artifactgraph*.mjs |
PATH launchers |
src/mcp/* |
MCP stdio + tools |
src/cli.ts |
CLI twin |
src/install/cursor-mcp.ts |
merge ~/.cursor/mcp.json |
src/analyze/* |
local intelligence |
stacks/*.json |
brownfield command presets |
platform-repos.json |
projectId → workspace relative root |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.