FileScopeMCP is a TypeScript-based MCP server that analyzes codebases to identify important files based on dependency relationships, providing AI tools with structural understanding of projects. It scans source files to detect imports across multiple languages (JavaScript, TypeScript, Python, C/C++, Rust, Lua, Zig), calculates importance scores (0-10) based on dependency patterns, and generates visualizations using Mermaid diagrams. The implementation features persistent storage of file trees, cross-platform path handling, and tools for querying file importance, finding critical components, and adding human-readable summaries to files, making it valuable for developers who want AI assistants to understand the architecture and significance of different files in their projects.
Nessuna recensione ancora. Sii il primo a recensire!
Accedi per unirti alla conversazione
Highlight AIBroker connection, queue depth, LLM progress, watcher state
Top files by importance score with dependency counts
Everything about a file: summary, concepts, change impact, exports, deps, staleness
Full file tree (no args) or flat top-N by importance (with maxItems)
Resolve a symbol name to file + line range; supports prefix match via trailing *
Find all symbols that call a named symbol (TS/JS call graph)
Find all symbols that a named symbol calls (TS/JS call graph)
Search file metadata across symbols, summaries, purpose, and paths
Files changed since a timestamp or git SHA
Louvain-clustered file groups by import coupling
Find circular dependency chains
Cycles involving a specific file
Queue files for LLM summarization via the broker
Point at a different project
Manually set or override a file's LLM summary
Manually set a file's importance score (0-10)
Drop files/patterns from tracking (destructive)
