$ loading_
Provide coding agents with a queryable architecture index for flow and dependencies.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "kernelee-mcp-tools" yet — see the docs or source repo.
Use kernelee-mcp-tools to query the control flow of paymentService.processOrder and list the key functions it calls in order.
A call chain or control-flow summary showing the execution path.
Use kernelee-mcp-tools to find which internal modules the auth module depends on, grouped into direct and indirect dependencies.
A dependency list with hierarchy, useful for impact analysis.
Use kernelee-mcp-tools to query the relationships among user onboarding components, including runtime wiring and static analysis results.
A summary of component relationships to quickly understand the system structure.
Developers can use it to provide a structured architecture index when AI works on complex projects. This helps agents query control flow and dependencies more accurately.
Before changing a module or function, teams can query its upstream and downstream dependencies. This makes it easier to see which components may be affected.
When system wiring is complex and call chains are unclear, this tool can expose static analysis and runtime connection information. It is useful for quickly locating relationships between components.
It is an MCP toolset for kernelee apps that combines static analysis and runtime wiring into a JSON architecture index. Coding agents can query control flow and dependencies through MCP.
It is mainly used to help coding agents understand code architecture, call relationships, and dependency structure. It is especially suitable for structured queries over large codebases.
The provided material does not include installation steps, runtime requirements, or key information. Please see the source repository for details.
Provides a live codebase architecture model for analysis and dependency tracing.
Retrieves company context and presents it as rules, reasoning, skills, and commands.
Give AI coding agents filesystem, Git, database, and compute tools via MCP.
Unified MCP tools for design insight, development help, and workflow acceleration.
Navigate codebases with architecture-aware symbol lookup and layered structural analysis.
Securely equips AI agents with executable tools for commands, search, and file operations.