$ loading_
Index your codebase so AI can inspect dependencies, call trees, and dead code.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Context Bunker MCP" yet — see the docs or source repo.
Using the current codebase index, list upstream and downstream dependencies of the payment module and identify the most tightly coupled files.
A dependency overview for the payment module, highlighting highly coupled files or key connection points.
Based on the AST index, trace the call tree for processOrder, showing which core functions it calls and what parts of the code call it.
A call tree for processOrder with a summary of inbound and outbound call relationships.
Scan the current project index and find potentially unreferenced functions, classes, or files, then rank them by risk.
A list of suspected dead code with evidence about whether each item is called or depended on.
When developers inherit an unfamiliar project, they can use it to help AI quickly map module dependencies, key call chains, and overall code organization from a structural index. This makes system understanding easier than relying on keyword search alone.
Before refactoring a function, class, or module, teams can inspect call trees and dependency relationships to see what will be affected. This helps identify highly coupled areas and reduce change risk.
After a project evolves over time, developers can use its dead code detection to find potentially unused functions, classes, or files. They can then review the findings manually before removing or archiving anything.
It is an MCP server that uses tree-sitter for AST parsing and indexes a codebase. AI tools can then quickly read structural information such as dependency graphs, call trees, and dead code signals from a local SQLite database.
The provided information says it indexes your local codebase and stores structural information in a local SQLite database. It does not mention any remote service or cloud indexing.
The available material does not include installation steps, runtime requirements, or configuration details. For exact prerequisites, see the source repository.
Analyze code structure and Git history while drastically reducing AI token usage.
Analyze codebases with semantic search, dependency insights, and natural language Q&A.
Help AI agents navigate, search, and understand codebases and change history.
Build persistent, semantically searchable memory for codebases via natural language queries.
Index source code locally to query symbols, dependencies, and tree structure.
Index local repositories for semantic search and structured code understanding.