Coderadius
@coderadius-ai
About Coderadius
Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI agents.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"coderadius": {
"args": [
"mcp",
"start"
],
"command": "cr"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Coderadius?
Coderadius is a static analysis tool that builds a live knowledge graph of your entire architecture across every service, API, queue, and database. It helps engineers and AI agents measure blast radius, enforce policy, and prevent cross-repo breaking changes before merge.
How to use Coderadius?
Install via npm i -g coderadius or the install script, then run cr init to configure, cr up to start the local graph database, cr analyze code . to build the graph, cr blast to check impact of current changes, and cr mcp start to start the MCP server for AI agents.
Key features of Coderadius
- Static architecture graph built from code
- Blast radius analysis with semantic exit codes
- Native MCP server for AI agent context
- Declarative governance as code with YAML policies
- Local-first: no code leaves your machine, supports Ollama
- Supports multiple languages and frameworks
Use cases of Coderadius
- Prevent accidental breaking changes across microservices
- Provide AI agents with context to avoid breaking downstream systems
- Enforce architectural policies without file-level linting
- Discover undocumented dependencies and coupling hotspots
- Trace data lineage across services and databases
FAQ from Coderadius
How does Coderadius differ from observability tools?
Coderadius builds its graph statically from code, not from runtime traffic, so it works before deployment.
What are the runtime requirements?
Docker for the local graph database and a self-contained binary for macOS or Linux. No other dependencies.
Is my code sent to external servers?
No. Coderadius is local-first; your code never leaves your machine. You can use a local LLM via Ollama or bring your own API key.
What frameworks and languages are supported?
Language support includes TypeScript, PHP, Python, Go, and Java. Several frameworks are eval-verified, others are heuristic+LLM.
How stable is the current release?
Coderadius is 0.x and moving fast. The deterministic core is well-tested, but LLM extraction quality varies and the CLI surface may change without migration paths.
Frequently asked questions
How does Coderadius differ from observability tools?
Coderadius builds its graph statically from code, not from runtime traffic, so it works before deployment.
What are the runtime requirements?
Docker for the local graph database and a self-contained binary for macOS or Linux. No other dependencies.
Is my code sent to external servers?
No. Coderadius is local-first; your code never leaves your machine. You can use a local LLM via Ollama or bring your own API key.
What frameworks and languages are supported?
Language support includes TypeScript, PHP, Python, Go, and Java. Several frameworks are eval-verified, others are heuristic+LLM.
How stable is the current release?
Coderadius is 0.x and moving fast. The deterministic core is well-tested, but LLM extraction quality varies and the CLI surface may change without migration paths.
Basic information
More Other MCP servers
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
Figs, Relationship Expert
Figs O'Sullivan, LMFTCouples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
Glasswarp
GlasswarpSee and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
ICSS
chokcoco不止于 CSS
Comments