deepviewLABSCO SUMMARY
A second model that has read everything.
Your IDE assistant works from the files it happened to open; this one answers with the whole repository in front of it. The cost is that the snapshot is only as current as the last time you regenerated the file.
What it is
An MCP server that lets Cursor, Windsurf and other MCP-capable IDEs put a question to Gemini with a whole codebase in context. You supply the codebase as a single file; the server sends it along with the question.
What you get
- One tool,
deepview: a requiredquestionabout the codebase, and an optionalcodebase_fileto load before answering - The model chosen at launch with
--model— the default isgemini-2.0-flash-lite - The codebase file pinned in the MCP config so every question hits the same snapshot, or supplied per call when you work across several projects
- Log level controlled with
--log-level, from DEBUG through CRITICAL
Requirements
Python 3.13+ and a Gemini API key from Google AI Studio, supplied as GEMINI_API_KEY. Install with pip install deepview-mcp. Your codebase has to arrive as one file — the author points at repomix to produce it, with an include and exclude list so vendored directories stay out. MIT.
Setup effort
One command plus a key — pip install deepview-mcp, then supply credentials
USE CASES
01
Asking where something is implemented
The question goes to a model holding the entire codebase, so the answer does not depend on which files were open.
02
Getting oriented in a repository you inherited
Pack it once, then ask architectural questions against the whole thing rather than reading in from the entry point.
03
Checking whether a change breaks something elsewhere
Ask what depends on the piece you are about to change, with every file in context.
04
Working across two codebases in one session
Leave the file argument out of the config and pass codebase_file per call to switch between them.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- pip on PATH
- Python 3.13+
- GEMINI_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install deepview-mcpMCP Clients
Cursor, Windsurf
JSON
{
"mcpServers": {
"deepview": {
"command": "<YOUR_PATH_TO_DEEPVIEW_MCP>",
"args": [],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}
