Coderadius MCP Server

Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI

Local serverstdioPython

What is the Coderadius MCP server?

Prevent cross-repo architectural breakage before merge. Architecture knowledge graph from static analysis, blast radius in CI, MCP server for AI agents. The coderadius mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 11 defined tools rather than through you.

What it actually does

  • 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

Its toolset

Everything the assistant can do here goes through one of these:

  • Languages — C#, Ruby
  • resolve_service_context — Orient the agent: map a file path, git remote, or repo name to its service, team, and repository
  • list_services — Inventory all services with owners, languages, and deployment topology
  • get_service_details — Deep-dive one service: exposed APIs, endpoint counts, deployment units, CI/CD and Docker infrastructure
  • get_repository_details — Repository posture: services, pipelines, Docker images, tool configurations, build tasks, commit liveness
  • get_data_contract — Exact schema (fields and types) of a payload, event, or database table, before modifying it
  • analyze_blast_radius — Upstream producers and downstream consumers of a resource (table, channel, endpoint)
  • evaluate_code_change_impact — Blast radius of a proposed change via in-memory topological diff, before committing
  • trace_data_lineage — Follow a data field across services, brokers, and APIs
  • analyze_architecture_gravity — SPOFs, shared-database anti-patterns, and coupling hotspots ranked by score
  • analyze_agentic_context — AI-tooling adoption per repository: tools, configurations, skills, workflows

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at coderadius on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Coderadius's toolset — Languages, resolve_service_context, list_services and 8 more — is a fair guide to whether it matches your workflow. It is maintained by coderadius-ai; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 11 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Coderadius.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the coderadius mcp server does with a few real requests.

Available tools

ToolWhat it does
LanguagesC#, Ruby
resolve_service_contextOrient the agent: map a file path, git remote, or repo name to its service, team, and repository.
list_servicesInventory all services with owners, languages, and deployment topology.
get_service_detailsDeep-dive one service: exposed APIs, endpoint counts, deployment units, CI/CD and Docker infrastructure.
get_repository_detailsRepository posture: services, pipelines, Docker images, tool configurations, build tasks, commit liveness.
get_data_contractExact schema (fields and types) of a payload, event, or database table, before modifying it.
analyze_blast_radiusUpstream producers and downstream consumers of a resource (table, channel, endpoint).
evaluate_code_change_impactBlast radius of a proposed change via in-memory topological diff, before committing.
trace_data_lineageFollow a data field across services, brokers, and APIs.
analyze_architecture_gravitySPOFs, shared-database anti-patterns, and coupling hotspots ranked by score.
analyze_agentic_contextAI-tooling adoption per repository: tools, configurations, skills, workflows.

How to install the Coderadius MCP server

{
  "mcpServers": {
    "coderadius": {
      "command": "cr",
      "args": ["mcp", "start"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Coderadius to Languages.
  • Use Coderadius to resolve service context.
  • Use Coderadius to list services.

Frequently asked questions

Coderadius builds its graph statically from code, not from runtime traffic, so it works before deployment.