Code-to-column change-impact knowledge graph for AI coding agents: the round trip from a screen to a database column and back, over MCP
A code-to-column change-impact knowledge graph for AI coding agents, and for the people who work beside them. Apache-2.0.
- A picture first - What it answers - Supported stacks - Install - Ten minutes on your own project - Set it up for your AI agent - The edit loop - Several projects, one server - Honesty, verify and doctor - The viewer - Profile and framework packs - How it is measured - Layout of the repository - Contributing, security, conduct - License
That is one column changed and the answer read in both directions, on two real open-source projects. The still shots below walk the same views one at a time.
Cascade answers one question in both directions: if I change this database column, which SQL statements, service methods, HTTP endpoints and user-facing screens are affected, and if I open this screen, which column does it end at? It answers over MCP so an AI coding agent can ask before it edits, and it draws the same answers in a local viewer so a person can read them.
Every edge carries its own grade, so an answer tells you exactly how far to trust it: what was proved, what is a sound candidate set, what is a hint. An AI agent reads that grade and knows whether it can act on an answer or should check it first, which is what makes an impact graph safe to hand to something that edits code on its own. What a parser cannot see, Cascade leaves out and says so: runtime wiring, reflection and AOP proxies are marked absent, never guessed. That calibration is the product, not a caveat.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/alexsoft-hq--Cascade.html)
LayerMap MCP: a layered map of your codebase for coding agents: callers, callees and the impact of a change, for TypeScript, JavaScript, Go, Python and Java. MCP server, CLI, and plugins for Claude Co
coderadius-ai/coderadiusPrevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI agents.
kanetran29/uigraphYour app generates its own verified UI transition graph — screens as nodes, guarded (event, effect) edges. Proof-gated verification, trust tiers, model-free MCP for AI agents.
tinhien11/tdai-memory-mcpLocal-first MCP memory server — Memory + CodeGraph + Wiki in one SQLite file. Tree-sitter code indexing, markdown wiki, lifecycle hooks, auto-capture. No API key, no cloud.
zamansheikh/memory-leanA token-lean MCP memory server for AI coding agents: a knowledge graph your agent can search without reading the whole thing. Drop-in replacement for the reference memory server.
okf-memory/okf-agent-memoryGit-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zer
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.