================== /// MCP /// /// FIL /// ================== [server:online] [protocol:ready]
FileScopeMCP
by admica
TypeScript MCP server that scans a project, ranks files by dependency-based importance, stores metadata in JSON, and serves it to AI tools (Cursor) with optional Mermaid diagram generation.
198
17
Open SourceInstallation
1. Prerequisites
• Python ≥3.10 installed and on PATH
• graphviz binary (dot) if you want diagram output – install with your OS package manager (e.g. `sudo apt-get install graphviz` or `brew install graphviz`).
2. Clone the repository
git clone https://github.com/admica/FileScopeMCP.git
cd FileScopeMCP
3. Install Python dependencies (a requirements.txt/pyproject file is expected in the repo)
python -m pip install -U pip
pip install -r requirements.txt # or: pip install .
4. (Optional) install Graphviz Python bindings if you want to post-process diagrams
pip install graphviz
5. Basic usage
# Analyse the current directory and write results to ./filescope_output
python -m filescope ./ --out ./filescope_output
6. Exporting diagrams only
python -m filescope ./ --diagram format=png
7. Integrate with MCP server
• Copy/merge the generated `filescope.json` & diagram artifacts into your MCP server’s context directory.
• Configure the MCP server to load the `filescope.json` file on startup (see API specs below).
Documentation
License: GNU General Public License v3.0
Updated 7/30/2025