FileScopeMCP
Analyzes your codebase identifying important files based on dependency relationships. Generates diagrams and importance scores per file, helping AI assistants understand the codebase. Automatically parses popular programming languages such as Python, C, C++, Rust, Zig, Lua.
FileScopeMCP
Your AI already knows how to code. Now it knows your codebase.
FileScopeMCP watches your code, ranks every file by importance, maps all dependencies, and keeps AI-generated summaries fresh in the background. When your LLM asks "what does this file do?" — it gets a real answer without reading the source.
Works with Claude Code, Cursor AI, or as a standalone daemon. Supports 12 languages out of the box.
Key Features
Importance ranking — every file scored 0-10 based on how many things depend on it, what it exports, and where it lives. Your LLM sees the critical files first.
Dependency mapping — bidirectional import tracking across Python, JS/TS, C/C++, Rust, Go, Ruby, Lua, Zig, PHP, C#, Java. Finds circular dependencies too.
Always fresh — file watcher + semantic change detection means metadata updates automatically. AST-level diffing for TS/JS, LLM-powered analysis for everything else. Only re-processes what actually changed.
LLM broker — a background process coordinates all AI work through llama.cpp's llama-server (or any OpenAI-compatible HTTP API). Priority queue ensures interactive queries beat background processing. Runs on a single GPU.
Nexus dashboard — a web UI at localhost:1234 that lets you visually explore your codebase across all your repos. Interactive dependency graphs, file detail panels, live broker activity, and per-repo health monitoring.
Quick Start
git clone https://github.com/admica/FileScopeMCP.git
cd FileScopeMCP
./build.sh # installs deps, compiles, registers with Claude Code
That's it. Open a Claude Code session in any project and FileScopeMCP auto-initializes. Try:
find_important_files(limit: 5)
status()
Want AI summaries? Run ./setup-llm.sh for a platform-specific guide to setting up llama.cpp's llama-server — see docs/llm-setup.md for details. Without it, everything else still works.
Add to your project's .gitignore:
.filescope/
.filescope-daemon.log
MCP Tools
| Tool | What it does |
|---|---|
find_important_files |
Top files by importance score |
get_file_summary |
Everything about a file: summary, concepts, change impact, deps, staleness |
list_files |
Full file tree with importance |
detect_cycles |
Find circular dependency chains |
status |
Broker connection, queue depth, LLM progress, watcher state |
scan_all |
Queue entire codebase for LLM processing |
set_base_directory |
Point at a different project |
set_file_summary / set_file_importance |
Manual overrides |
exclude_and_remove |
Drop files/patterns from tracking |
get_cycles_for_file |
Cycles involving a specific file |
Nexus Dashboard
npm run nexus # opens at http://localhost:1234
A read-only web dashboard that connects to every FileScopeMCP repo on your machine:
- Project view — file tree with importance heat colors and staleness indicators, click any file for full metadata
- Dependency graph — interactive Cytoscape.js visualization, filter by directory, click nodes to inspect
- System view — live broker status, per-repo token usage, streaming activity log
- Settings — manage which repos appear, remove or restore from blacklist
Auto-discovers repos by scanning for .filescope/data.db directories. No configuration needed.
How It Works
Your code changes
→ file watcher picks it up
→ AST diff classifies the change (exports? types? body only?)
→ importance scores recalculated
→ staleness cascades to dependents (only if exports/types changed)
→ LLM broker regenerates summaries, concepts, change impact
→ your AI's next query gets fresh answers
Everything lives in .filescope/data.db (SQLite, WAL mode) per project. The broker coordinates LLM work across all your repos via a Unix socket at ~/.filescope/broker.sock.
Documentation
| Doc | What's in it |
|---|---|
| LLM Setup | llama.cpp / llama-server installation — local, WSL2+Windows, or remote |
| Configuration | Per-project config, broker config, ignore patterns |
| MCP Clients | Setup for Claude Code, Cursor AI, daemon mode |
| Troubleshooting | Common issues and fixes |
| Internals | Dependency detection, importance formula, cascade engine, storage |
License
Copyright (c) 2026 admica. All rights reserved. See LICENSE.
Recommend MCP Servers 💡
agentql-mcp
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
@dndzgz/mcp
MCP server providing real-time Zaragoza bus, tram, and Bizi bike service information
anki-mcp-server
An MCP server that connects to a locally running Anki desktop app via the Anki-Connect add-on, providing functionalities for card review, creation, and search.
lspace-server
Lspace is an open-source MCP server and standalone application that captures insights from AI sessions, making them available across tools for persistent, searchable knowledge.
glean-mcp-server
An MCP server implementation integrating Glean API for Search and Chat functions.
microcms-api-mcp-server
Model Context Protocol (MCP) を使用して microCMS の API にアクセスするサーバで、コンテンツ一覧取得、特定コンテンツ取得、コンテンツ検索、フィルター検索などの機能を提供します。