| Name | deepview-mcp JSON |
| Version |
0.2.4
JSON |
| download |
| home_page | None |
| Summary | A Model Context Protocol server for analyzing large codebases using Gemini 2.0 |
| upload_time | 2025-08-07 09:51:15 |
| maintainer | None |
| docs_url | None |
| author | Dmitry Degtyarev |
| requires_python | <4.0,>=3.10 |
| license | MIT |
| keywords |
mcp
gemini
code-analysis
ai
ide
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
[](https://mseep.ai/app/ai-1st-deepview-mcp)
# DeepView MCP
DeepView MCP is a Model Context Protocol server that enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini's extensive context window.
[](https://badge.fury.io/py/deepview-mcp)
[](https://smithery.ai/server/@ai-1st/deepview-mcp)
## Features
- Load an entire codebase from a single text file (e.g., created with tools like repomix)
- Query the codebase using Gemini's large context window
- Connect to IDEs that support the MCP protocol, like Cursor and Windsurf
- Configurable Gemini model selection via command-line arguments
## Prerequisites
- Python 3.13+
- Gemini API key from [Google AI Studio](https://aistudio.google.com/)
## Installation
### Installing via Smithery
To install DeepView for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@ai-1st/deepview-mcp):
```bash
npx -y @smithery/cli install @ai-1st/deepview-mcp --client claude
```
### Using pip
```bash
pip install deepview-mcp
```
## Usage
### Starting the Server
Note: you don't need to start the server manually. These parameters are configured in your MCP setup in your IDE (see below).
```bash
# Basic usage with default settings
deepview-mcp [path/to/codebase.txt]
# Specify a different Gemini model
deepview-mcp [path/to/codebase.txt] --model gemini-2.0-pro
# Change log level
deepview-mcp [path/to/codebase.txt] --log-level DEBUG
```
The codebase file parameter is optional. If not provided, you'll need to specify it when making queries.
### Command-line Options
- `--model MODEL`: Specify the Gemini model to use (default: gemini-2.0-flash-lite)
- `--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}`: Set the logging level (default: INFO)
### Using with an IDE (Cursor/Windsurf/...)
1. Open IDE settings
2. Navigate to the MCP configuration
3. Add a new MCP server with the following configuration:
```json
{
"mcpServers": {
"deepview": {
"command": "/path/to/deepview-mcp",
"args": [],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key"
}
}
}
}
Setting a codebase file is optional. If you are working with the same codebase, you can set the default codebase file using the following configuration:
```json
{
"mcpServers": {
"deepview": {
"command": "/path/to/deepview-mcp",
"args": ["/path/to/codebase.txt"],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key"
}
}
}
}
```
Here's how to specify the Gemini version to use:
```json
{
"mcpServers": {
"deepview": {
"command": "/path/to/deepview-mcp",
"args": ["--model", "gemini-2.5-pro-exp-03-25"],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key"
}
}
}
}
```
4. Reload MCP servers configuration
### Available Tools
The server provides one tool:
1. `deepview`: Ask a question about the codebase
- Required parameter: `question` - The question to ask about the codebase
- Optional parameter: `codebase_file` - Path to a codebase file to load before querying
## Preparing Your Codebase
DeepView MCP requires a single file containing your entire codebase. You can use [repomix](https://github.com/yamadashy/repomix) to prepare your codebase in an AI-friendly format.
### Using repomix
1. **Basic Usage**: Run repomix in your project directory to create a default output file:
```bash
# Make sure you're using Node.js 18.17.0 or higher
npx repomix
```
This will generate a `repomix-output.xml` file containing your codebase.
2. **Custom Configuration**: Create a configuration file to customize which files get packaged and the output format:
```bash
npx repomix --init
```
This creates a `repomix.config.json` file that you can edit to:
- Include/exclude specific files or directories
- Change the output format (XML, JSON, TXT)
- Set the output filename
- Configure other packaging options
### Example repomix Configuration
Here's an example `repomix.config.json` file:
```json
{
"include": [
"**/*.py",
"**/*.js",
"**/*.ts",
"**/*.jsx",
"**/*.tsx"
],
"exclude": [
"node_modules/**",
"venv/**",
"**/__pycache__/**",
"**/test/**"
],
"output": {
"format": "xml",
"filename": "my-codebase.xml"
}
}
```
For more information on repomix, visit the [repomix GitHub repository](https://github.com/yamadashy/repomix).
## License
MIT
## Author
Dmitry Degtyarev (ddegtyarev@gmail.com)
Raw data
{
"_id": null,
"home_page": null,
"name": "deepview-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": "mcp, gemini, code-analysis, ai, ide",
"author": "Dmitry Degtyarev",
"author_email": "ddegtyarev@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/c3/a3/c1b239faa2e26cc1ede2ae02beec5f9c1abb83aa5443ed4e86ac4712cce4/deepview_mcp-0.2.4.tar.gz",
"platform": null,
"description": "[](https://mseep.ai/app/ai-1st-deepview-mcp)\n\n# DeepView MCP\n\nDeepView MCP is a Model Context Protocol server that enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini's extensive context window.\n\n[](https://badge.fury.io/py/deepview-mcp)\n[](https://smithery.ai/server/@ai-1st/deepview-mcp)\n\n## Features\n\n- Load an entire codebase from a single text file (e.g., created with tools like repomix)\n- Query the codebase using Gemini's large context window\n- Connect to IDEs that support the MCP protocol, like Cursor and Windsurf\n- Configurable Gemini model selection via command-line arguments\n\n## Prerequisites\n\n- Python 3.13+\n- Gemini API key from [Google AI Studio](https://aistudio.google.com/)\n\n## Installation\n\n### Installing via Smithery\n\nTo install DeepView for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@ai-1st/deepview-mcp):\n\n```bash\nnpx -y @smithery/cli install @ai-1st/deepview-mcp --client claude\n```\n\n### Using pip\n\n```bash\npip install deepview-mcp\n```\n\n## Usage\n\n### Starting the Server\n\nNote: you don't need to start the server manually. These parameters are configured in your MCP setup in your IDE (see below).\n\n```bash\n# Basic usage with default settings\ndeepview-mcp [path/to/codebase.txt]\n\n# Specify a different Gemini model\ndeepview-mcp [path/to/codebase.txt] --model gemini-2.0-pro\n\n# Change log level\ndeepview-mcp [path/to/codebase.txt] --log-level DEBUG\n```\n\nThe codebase file parameter is optional. If not provided, you'll need to specify it when making queries.\n\n### Command-line Options\n\n- `--model MODEL`: Specify the Gemini model to use (default: gemini-2.0-flash-lite)\n- `--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}`: Set the logging level (default: INFO)\n\n### Using with an IDE (Cursor/Windsurf/...)\n\n1. Open IDE settings\n2. Navigate to the MCP configuration\n3. Add a new MCP server with the following configuration:\n ```json\n {\n \"mcpServers\": {\n \"deepview\": {\n \"command\": \"/path/to/deepview-mcp\",\n \"args\": [],\n \"env\": {\n \"GEMINI_API_KEY\": \"your_gemini_api_key\"\n }\n }\n }\n }\n\nSetting a codebase file is optional. If you are working with the same codebase, you can set the default codebase file using the following configuration:\n ```json\n {\n \"mcpServers\": {\n \"deepview\": {\n \"command\": \"/path/to/deepview-mcp\",\n \"args\": [\"/path/to/codebase.txt\"],\n \"env\": {\n \"GEMINI_API_KEY\": \"your_gemini_api_key\"\n }\n }\n }\n }\n ```\n\nHere's how to specify the Gemini version to use:\n\n```json\n{\n \"mcpServers\": {\n \"deepview\": {\n \"command\": \"/path/to/deepview-mcp\",\n \"args\": [\"--model\", \"gemini-2.5-pro-exp-03-25\"],\n \"env\": {\n \"GEMINI_API_KEY\": \"your_gemini_api_key\"\n }\n }\n }\n}\n```\n\n4. Reload MCP servers configuration\n\n\n### Available Tools\n\nThe server provides one tool:\n\n1. `deepview`: Ask a question about the codebase\n - Required parameter: `question` - The question to ask about the codebase\n - Optional parameter: `codebase_file` - Path to a codebase file to load before querying\n\n## Preparing Your Codebase\n\nDeepView MCP requires a single file containing your entire codebase. You can use [repomix](https://github.com/yamadashy/repomix) to prepare your codebase in an AI-friendly format.\n\n### Using repomix\n\n1. **Basic Usage**: Run repomix in your project directory to create a default output file:\n\n```bash\n# Make sure you're using Node.js 18.17.0 or higher\nnpx repomix\n```\n\nThis will generate a `repomix-output.xml` file containing your codebase.\n\n2. **Custom Configuration**: Create a configuration file to customize which files get packaged and the output format:\n\n```bash\nnpx repomix --init\n```\n\nThis creates a `repomix.config.json` file that you can edit to:\n- Include/exclude specific files or directories\n- Change the output format (XML, JSON, TXT)\n- Set the output filename\n- Configure other packaging options\n\n### Example repomix Configuration\n\nHere's an example `repomix.config.json` file:\n\n```json\n{\n \"include\": [\n \"**/*.py\",\n \"**/*.js\",\n \"**/*.ts\",\n \"**/*.jsx\",\n \"**/*.tsx\"\n ],\n \"exclude\": [\n \"node_modules/**\",\n \"venv/**\",\n \"**/__pycache__/**\",\n \"**/test/**\"\n ],\n \"output\": {\n \"format\": \"xml\",\n \"filename\": \"my-codebase.xml\"\n }\n}\n```\n\nFor more information on repomix, visit the [repomix GitHub repository](https://github.com/yamadashy/repomix).\n\n## License\n\nMIT\n\n## Author\n\nDmitry Degtyarev (ddegtyarev@gmail.com)\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Model Context Protocol server for analyzing large codebases using Gemini 2.0",
"version": "0.2.4",
"project_urls": {
"Repository": "https://github.com/ddegtyarev/deepview-mcp"
},
"split_keywords": [
"mcp",
" gemini",
" code-analysis",
" ai",
" ide"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "e2699c9885e3ce7c9d38bab42eb71bf9831205cd496af8b2d2f1be10278e9bf6",
"md5": "ac9d9d4e4d93783aa811cc5eabcce1aa",
"sha256": "e6c1e8521f53bdd82ad6006a82a19ecaf352cc9553ecba812aecfdb833ae4dc9"
},
"downloads": -1,
"filename": "deepview_mcp-0.2.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ac9d9d4e4d93783aa811cc5eabcce1aa",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 8934,
"upload_time": "2025-08-07T09:51:14",
"upload_time_iso_8601": "2025-08-07T09:51:14.189869Z",
"url": "https://files.pythonhosted.org/packages/e2/69/9c9885e3ce7c9d38bab42eb71bf9831205cd496af8b2d2f1be10278e9bf6/deepview_mcp-0.2.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "c3a3c1b239faa2e26cc1ede2ae02beec5f9c1abb83aa5443ed4e86ac4712cce4",
"md5": "200c8537d32c91a4c5219cdeda28a2c7",
"sha256": "085d5c3e81037e5fd5601d7e267445420cfbaa2cff7cf0b9e718827c03d7f9c1"
},
"downloads": -1,
"filename": "deepview_mcp-0.2.4.tar.gz",
"has_sig": false,
"md5_digest": "200c8537d32c91a4c5219cdeda28a2c7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 6633,
"upload_time": "2025-08-07T09:51:15",
"upload_time_iso_8601": "2025-08-07T09:51:15.127171Z",
"url": "https://files.pythonhosted.org/packages/c3/a3/c1b239faa2e26cc1ede2ae02beec5f9c1abb83aa5443ed4e86ac4712cce4/deepview_mcp-0.2.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-07 09:51:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "ddegtyarev",
"github_project": "deepview-mcp",
"github_not_found": true,
"lcname": "deepview-mcp"
}
