Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI agents.
Prevent cross-repo architectural breakage before merge.
As teams adopt AI coding tools, code is written faster than ever, but without global system context. CodeRadius statically builds a live knowledge graph of your entire architecture, covering every service, API, queue, and database across every repo, so engineers and AI agents can measure blast radius, enforce policy, and ship without breaking downstream systems.
An innocent-looking rename in order-service; cr blast finds the consumer it breaks in notification-service, in seconds. Explore the live demo dashboard →
AI coding agents are fast but architecturally blind. They will flawlessly refactor an API payload or rename a database field, unaware they just broke a downstream consumer three teams away. Even without AI, undocumented dependencies accumulate until every cross-service change turns into an archaeological dig.
CodeRadius fixes this with three capabilities on one graph:
- Blast radius before merge: cr blast is terraform plan for architecture. It provides an in-memory topological diff of your changes against the graph, returning structured findings in seconds. Semantic exit codes (0 SAFE, 1 WATCH, 2 BREAKING) let CI and agents branch without parsing text. - Live context for AI agents: A native MCP server lets any agent query data contracts, downstream consumers, and change impact before writing code. - Governance as code: Declarative YAML policies evaluated against the live architecture graph, not file-level lint: unowned services, deprecated dependencies on exposed APIs, shared-database anti-patterns.
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/coderadius-ai--coderadius.html)
A map of all your repos for coding agents: one index, one card per repo, an MCP server. Works with Claude Code, Codex, Gemini CLI and Cursor.
pranee54/AgentDoctorLocal CLI that audits coding-agent configuration for security, instructions, context, and MCP — no API key or code upload by default.
coffeecoproject/layermapLayerMap 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
friday-memory/friday⚡ The open-source persistent cognitive memory layer for AI coding agents. Stop your Cursor, Claude & Copilot from having amnesia.
Koragraph/KoragraphMCPThe memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down.
VictorAgahi/causalmeshMCP server that gives your AI coding agent a map of your polyglot codebase — reverse dependencies, gRPC tracing, event/topic flows, and doc search, without burning context. Single local Rust binary, n
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.