# RMCP: R Model Context Protocol Server
[](https://pypi.org/project/rmcp/)
[](https://pepy.tech/project/rmcp)
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
**Version 0.3.2** - A comprehensive Model Context Protocol (MCP) server with 33 statistical analysis tools across 8 categories. RMCP enables AI assistants and applications to perform sophisticated statistical modeling, econometric analysis, machine learning, time series analysis, and data science tasks seamlessly through natural conversation.
**🎉 Now with 33 statistical tools across 8 categories!**
## 🚀 Quick Start
```bash
pip install rmcp
```
```bash
# Start the MCP server
rmcp start
```
That's it! RMCP is now ready to handle statistical analysis requests via the Model Context Protocol.
**👉 [See Working Examples →](examples/quick_start_guide.md)** - Copy-paste ready commands with real datasets!
## ✨ Features
### 📊 Comprehensive Statistical Analysis (33 Tools)
#### **Regression & Correlation** ✅
- **Linear Regression** (`linear_model`): OLS with robust standard errors, R², p-values
- **Logistic Regression** (`logistic_regression`): Binary classification with odds ratios and accuracy
- **Correlation Analysis** (`correlation_analysis`): Pearson, Spearman, and Kendall correlations
#### **Time Series Analysis** ✅
- **ARIMA Modeling** (`arima_model`): Autoregressive integrated moving average with forecasting
- **Time Series Decomposition** (`decompose_timeseries`): Trend, seasonal, remainder components
- **Stationarity Testing** (`stationarity_test`): ADF, KPSS, Phillips-Perron tests
#### **Data Transformation** ✅
- **Lag/Lead Variables** (`lag_lead`): Create time-shifted variables for analysis
- **Winsorization** (`winsorize`): Handle outliers by capping extreme values
- **Differencing** (`difference`): Create stationary series for time series analysis
- **Standardization** (`standardize`): Z-score, min-max, robust scaling
#### **Statistical Testing** ✅
- **T-Tests** (`t_test`): One-sample, two-sample, paired t-tests
- **ANOVA** (`anova`): Analysis of variance with Types I/II/III
- **Chi-Square Tests** (`chi_square_test`): Independence and goodness-of-fit
- **Normality Tests** (`normality_test`): Shapiro-Wilk, Jarque-Bera, Anderson-Darling
#### **Descriptive Statistics** ✅
- **Summary Statistics** (`summary_stats`): Comprehensive descriptives with grouping
- **Outlier Detection** (`outlier_detection`): IQR, Z-score, Modified Z-score methods
- **Frequency Tables** (`frequency_table`): Counts and percentages with sorting
#### **Advanced Econometrics** ✅
- **Panel Regression** (`panel_regression`): Fixed/random effects for longitudinal data
- **Instrumental Variables** (`instrumental_variables`): 2SLS with endogeneity testing
- **Vector Autoregression** (`var_model`): Multivariate time series modeling
#### **Machine Learning** ✅
- **K-Means Clustering** (`kmeans_clustering`): Unsupervised clustering with validation
- **Decision Trees** (`decision_tree`): Classification and regression trees
- **Random Forest** (`random_forest`): Ensemble methods with variable importance
#### **Data Visualization** ✅
- **Scatter Plots** (`scatter_plot`): Correlation plots with trend lines
- **Histograms** (`histogram`): Distribution analysis with density overlay
- **Box Plots** (`boxplot`): Quartile analysis with outlier detection
- **Time Series Plots** (`time_series_plot`): Temporal data visualization
- **Correlation Heatmaps** (`correlation_heatmap`): Matrix visualization
- **Regression Diagnostics** (`regression_plot`): Model validation plots
#### **File Operations** ✅
- **CSV Import** (`read_csv`): Flexible data loading with parsing options
- **CSV Export** (`write_csv`): Data export with formatting control
- **Dataset Information** (`data_info`): Comprehensive data structure analysis
- **Data Filtering** (`filter_data`): Complex conditional data selection
### Production Ready
- **MCP Protocol**: Full JSON-RPC 2.0 compliance
- **Transport Agnostic**: stdio, HTTP, WebSocket support
- **Error Handling**: Comprehensive error reporting and validation
- **Security**: Safe R execution with controlled environment
## 🎯 Real-World Usage
RMCP works through natural conversation with AI assistants. Here's how users actually interact with it:
### Business Analysis
**You ask Claude:**
> *"I have sales data and marketing spend. Can you analyze the ROI and tell me how effective our marketing is?"*
**Claude responds:**
> *"Based on the regression analysis, every $1 spent on marketing generates $4.70 in additional sales. The relationship is highly significant (p < 0.001) and explains 97.9% of sales variation."*
### Economic Research
**You ask Claude:**
> *"I have GDP growth and unemployment data for several countries. Can you test if this supports Okun's Law?"*
**Claude responds:**
> *"The correlation analysis shows strong support for Okun's Law with r = -0.944. Higher GDP growth is strongly associated with lower unemployment across your dataset."*
### Data Science
**You ask Claude:**
> *"Help me build a customer churn prediction model using tenure and monthly charges."*
**Claude responds:**
> *"I've built a logistic regression model that achieves 100% accuracy. Longer tenure significantly reduces churn risk (11.3% less likely per month), while higher charges increase churn risk (3% more likely per dollar)."*
## 📊 Validated User Scenarios
RMCP has been tested with real-world scenarios achieving **100% success rate**:
- ✅ **Business Analysts**: Sales forecasting with 97.9% R², $4.70 ROI per marketing dollar
- ✅ **Economists**: Macroeconomic analysis showing Okun's Law (r=-0.944)
- ✅ **Data Scientists**: Customer churn prediction with 100% accuracy
- ✅ **Researchers**: Treatment effect analysis with significant results (p<0.001)
## 🔧 Installation & Setup
### Prerequisites
- Python 3.8+
- R 4.0+ (automatically configured)
### Install via pip
```bash
pip install rmcp
```
### Development Installation
```bash
git clone https://github.com/gojiplus/rmcp.git
cd rmcp
pip install -e ".[dev]"
```
### With Claude Desktop
Add to your Claude Desktop MCP configuration:
```json
{
"mcpServers": {
"rmcp": {
"command": "rmcp",
"args": ["start"],
"env": {}
}
}
}
```
## 📚 Usage
### Command Line Interface
```bash
# Start MCP server (stdio transport)
rmcp start
# Check version
rmcp --version
# Advanced server configuration
rmcp serve --log-level DEBUG --read-only
# List available tools and capabilities
rmcp list-capabilities
```
### Programmatic Usage
```python
# RMCP is primarily designed as a CLI MCP server
# For programmatic R analysis, use the MCP protocol:
import json
import subprocess
# Send analysis request to RMCP server
request = {
"tool": "linear_model",
"args": {
"formula": "y ~ x",
"data": {"x": [1, 2, 3], "y": [2, 4, 6]}
}
}
# Start server and send request via stdin
proc = subprocess.Popen(['rmcp', 'start'],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True)
result, _ = proc.communicate(json.dumps(request))
print(result)
```
### API Examples
#### Linear Regression
```python
{
"tool": "linear_model",
"args": {
"formula": "outcome ~ treatment + age + baseline",
"data": {
"outcome": [4.2, 6.8, 3.8, 7.1],
"treatment": [0, 1, 0, 1],
"age": [25, 30, 22, 35],
"baseline": [3.8, 4.2, 3.5, 4.8]
}
}
}
```
#### Correlation Analysis
```python
{
"tool": "correlation_analysis",
"args": {
"data": {
"x": [1, 2, 3, 4, 5],
"y": [2, 4, 6, 8, 10]
},
"variables": ["x", "y"],
"method": "pearson"
}
}
```
#### Logistic Regression
```python
{
"tool": "logistic_regression",
"args": {
"formula": "churn ~ tenure_months + monthly_charges",
"data": {
"churn": [0, 1, 0, 1],
"tenure_months": [24, 6, 36, 3],
"monthly_charges": [70, 85, 65, 90]
},
"family": "binomial",
"link": "logit"
}
}
```
## 🧪 Testing & Validation
RMCP includes comprehensive testing with realistic scenarios:
```bash
# Run all user scenarios (should show 100% pass rate)
python tests/realistic_scenarios.py
# Run development test script
bash src/rmcp/scripts/test.sh
```
**Current Test Coverage**:
- ✅ **MCP Interface**: 100% success rate (5/5 tests) - Validates actual Claude Desktop integration
- ✅ **User Scenarios**: 100% success rate (4/4 tests) - Validates real-world usage patterns
- ✅ **Conversational Examples**: All documented examples tested and verified working
## 🏗️ Architecture
RMCP is built with production best practices:
- **Clean Architecture**: Modular design with clear separation of concerns
- **MCP Compliance**: Full Model Context Protocol specification support
- **Transport Layer**: Pluggable transports (stdio, HTTP, WebSocket)
- **R Integration**: Safe subprocess execution with JSON serialization
- **Error Handling**: Comprehensive error reporting and recovery
- **Security**: Controlled R execution environment
```
src/rmcp/
├── core/ # MCP server core
├── tools/ # Statistical analysis tools
├── transport/ # Communication layers
├── registries/ # Tool and resource management
└── security/ # Safe execution environment
```
## 🤝 Contributing
We welcome contributions! Please see our [contributing guidelines](CONTRIBUTING.md).
### Development Setup
```bash
git clone https://github.com/gojiplus/rmcp.git
cd rmcp
pip install -e ".[dev]"
pre-commit install
```
### Running Tests
```bash
python tests/realistic_scenarios.py # User scenarios
pytest tests/ # Unit tests (if any)
```
## 📄 License
MIT License - see [LICENSE](LICENSE) file for details.
## 🙋 Support
- 📖 **Documentation**: See [Quick Start Guide](examples/quick_start_guide.md) for working examples
- 🐛 **Issues**: [GitHub Issues](https://github.com/gojiplus/rmcp/issues)
- 💬 **Discussions**: [GitHub Discussions](https://github.com/gojiplus/rmcp/discussions)
## 🎉 Acknowledgments
RMCP builds on the excellent work of:
- [Model Context Protocol](https://modelcontextprotocol.io/) specification
- [R Project](https://www.r-project.org/) statistical computing environment
- The broader open-source statistical computing community
---
**Ready to analyze data like never before?** Install RMCP and start running sophisticated statistical analyses through AI assistants today! 🚀
Raw data
{
"_id": null,
"home_page": null,
"name": "rmcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "mcp, r, statistics, econometrics, model-context-protocol, data-analysis",
"author": null,
"author_email": "Gaurav Sood <gsood07@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/7b/88/ab27c67ee6886b33531d07b106f46aede09b4cfb404d9c7672ec31554b7a/rmcp-0.3.2.tar.gz",
"platform": null,
"description": "# RMCP: R Model Context Protocol Server\n\n[](https://pypi.org/project/rmcp/)\n[](https://pepy.tech/project/rmcp)\n[](https://opensource.org/licenses/MIT)\n[](https://www.python.org/downloads/)\n\n**Version 0.3.2** - A comprehensive Model Context Protocol (MCP) server with 33 statistical analysis tools across 8 categories. RMCP enables AI assistants and applications to perform sophisticated statistical modeling, econometric analysis, machine learning, time series analysis, and data science tasks seamlessly through natural conversation.\n\n**\ud83c\udf89 Now with 33 statistical tools across 8 categories!**\n\n## \ud83d\ude80 Quick Start\n\n```bash\npip install rmcp\n```\n\n```bash\n# Start the MCP server\nrmcp start\n```\n\nThat's it! RMCP is now ready to handle statistical analysis requests via the Model Context Protocol.\n\n**\ud83d\udc49 [See Working Examples \u2192](examples/quick_start_guide.md)** - Copy-paste ready commands with real datasets!\n\n## \u2728 Features\n\n### \ud83d\udcca Comprehensive Statistical Analysis (33 Tools)\n\n#### **Regression & Correlation** \u2705\n- **Linear Regression** (`linear_model`): OLS with robust standard errors, R\u00b2, p-values\n- **Logistic Regression** (`logistic_regression`): Binary classification with odds ratios and accuracy \n- **Correlation Analysis** (`correlation_analysis`): Pearson, Spearman, and Kendall correlations\n\n#### **Time Series Analysis** \u2705\n- **ARIMA Modeling** (`arima_model`): Autoregressive integrated moving average with forecasting\n- **Time Series Decomposition** (`decompose_timeseries`): Trend, seasonal, remainder components\n- **Stationarity Testing** (`stationarity_test`): ADF, KPSS, Phillips-Perron tests\n\n#### **Data Transformation** \u2705\n- **Lag/Lead Variables** (`lag_lead`): Create time-shifted variables for analysis\n- **Winsorization** (`winsorize`): Handle outliers by capping extreme values\n- **Differencing** (`difference`): Create stationary series for time series analysis\n- **Standardization** (`standardize`): Z-score, min-max, robust scaling\n\n#### **Statistical Testing** \u2705\n- **T-Tests** (`t_test`): One-sample, two-sample, paired t-tests\n- **ANOVA** (`anova`): Analysis of variance with Types I/II/III\n- **Chi-Square Tests** (`chi_square_test`): Independence and goodness-of-fit\n- **Normality Tests** (`normality_test`): Shapiro-Wilk, Jarque-Bera, Anderson-Darling\n\n#### **Descriptive Statistics** \u2705\n- **Summary Statistics** (`summary_stats`): Comprehensive descriptives with grouping\n- **Outlier Detection** (`outlier_detection`): IQR, Z-score, Modified Z-score methods\n- **Frequency Tables** (`frequency_table`): Counts and percentages with sorting\n\n#### **Advanced Econometrics** \u2705\n- **Panel Regression** (`panel_regression`): Fixed/random effects for longitudinal data\n- **Instrumental Variables** (`instrumental_variables`): 2SLS with endogeneity testing\n- **Vector Autoregression** (`var_model`): Multivariate time series modeling\n\n#### **Machine Learning** \u2705\n- **K-Means Clustering** (`kmeans_clustering`): Unsupervised clustering with validation\n- **Decision Trees** (`decision_tree`): Classification and regression trees\n- **Random Forest** (`random_forest`): Ensemble methods with variable importance\n\n#### **Data Visualization** \u2705\n- **Scatter Plots** (`scatter_plot`): Correlation plots with trend lines\n- **Histograms** (`histogram`): Distribution analysis with density overlay\n- **Box Plots** (`boxplot`): Quartile analysis with outlier detection\n- **Time Series Plots** (`time_series_plot`): Temporal data visualization\n- **Correlation Heatmaps** (`correlation_heatmap`): Matrix visualization\n- **Regression Diagnostics** (`regression_plot`): Model validation plots\n\n#### **File Operations** \u2705\n- **CSV Import** (`read_csv`): Flexible data loading with parsing options\n- **CSV Export** (`write_csv`): Data export with formatting control\n- **Dataset Information** (`data_info`): Comprehensive data structure analysis\n- **Data Filtering** (`filter_data`): Complex conditional data selection\n\n### Production Ready\n- **MCP Protocol**: Full JSON-RPC 2.0 compliance\n- **Transport Agnostic**: stdio, HTTP, WebSocket support\n- **Error Handling**: Comprehensive error reporting and validation\n- **Security**: Safe R execution with controlled environment\n\n## \ud83c\udfaf Real-World Usage\n\nRMCP works through natural conversation with AI assistants. Here's how users actually interact with it:\n\n### Business Analysis\n**You ask Claude:**\n> *\"I have sales data and marketing spend. Can you analyze the ROI and tell me how effective our marketing is?\"*\n\n**Claude responds:**\n> *\"Based on the regression analysis, every $1 spent on marketing generates $4.70 in additional sales. The relationship is highly significant (p < 0.001) and explains 97.9% of sales variation.\"*\n\n### Economic Research \n**You ask Claude:**\n> *\"I have GDP growth and unemployment data for several countries. Can you test if this supports Okun's Law?\"*\n\n**Claude responds:**\n> *\"The correlation analysis shows strong support for Okun's Law with r = -0.944. Higher GDP growth is strongly associated with lower unemployment across your dataset.\"*\n\n### Data Science\n**You ask Claude:**\n> *\"Help me build a customer churn prediction model using tenure and monthly charges.\"*\n\n**Claude responds:**\n> *\"I've built a logistic regression model that achieves 100% accuracy. Longer tenure significantly reduces churn risk (11.3% less likely per month), while higher charges increase churn risk (3% more likely per dollar).\"*\n\n## \ud83d\udcca Validated User Scenarios\n\nRMCP has been tested with real-world scenarios achieving **100% success rate**:\n\n- \u2705 **Business Analysts**: Sales forecasting with 97.9% R\u00b2, $4.70 ROI per marketing dollar\n- \u2705 **Economists**: Macroeconomic analysis showing Okun's Law (r=-0.944) \n- \u2705 **Data Scientists**: Customer churn prediction with 100% accuracy\n- \u2705 **Researchers**: Treatment effect analysis with significant results (p<0.001)\n\n## \ud83d\udd27 Installation & Setup\n\n### Prerequisites\n- Python 3.8+\n- R 4.0+ (automatically configured)\n\n### Install via pip\n```bash\npip install rmcp\n```\n\n### Development Installation\n```bash\ngit clone https://github.com/gojiplus/rmcp.git\ncd rmcp\npip install -e \".[dev]\"\n```\n\n### With Claude Desktop\n\nAdd to your Claude Desktop MCP configuration:\n\n```json\n{\n \"mcpServers\": {\n \"rmcp\": {\n \"command\": \"rmcp\",\n \"args\": [\"start\"],\n \"env\": {}\n }\n }\n}\n```\n\n## \ud83d\udcda Usage\n\n### Command Line Interface\n\n```bash\n# Start MCP server (stdio transport)\nrmcp start\n\n# Check version\nrmcp --version\n\n# Advanced server configuration \nrmcp serve --log-level DEBUG --read-only\n\n# List available tools and capabilities\nrmcp list-capabilities\n```\n\n### Programmatic Usage\n\n```python\n# RMCP is primarily designed as a CLI MCP server\n# For programmatic R analysis, use the MCP protocol:\n\nimport json\nimport subprocess\n\n# Send analysis request to RMCP server\nrequest = {\n \"tool\": \"linear_model\",\n \"args\": {\n \"formula\": \"y ~ x\",\n \"data\": {\"x\": [1, 2, 3], \"y\": [2, 4, 6]}\n }\n}\n\n# Start server and send request via stdin\nproc = subprocess.Popen(['rmcp', 'start'], \n stdin=subprocess.PIPE, \n stdout=subprocess.PIPE, \n stderr=subprocess.PIPE, \n text=True)\nresult, _ = proc.communicate(json.dumps(request))\nprint(result)\n```\n\n### API Examples\n\n#### Linear Regression\n```python\n{\n \"tool\": \"linear_model\",\n \"args\": {\n \"formula\": \"outcome ~ treatment + age + baseline\", \n \"data\": {\n \"outcome\": [4.2, 6.8, 3.8, 7.1],\n \"treatment\": [0, 1, 0, 1],\n \"age\": [25, 30, 22, 35],\n \"baseline\": [3.8, 4.2, 3.5, 4.8]\n }\n }\n}\n```\n\n#### Correlation Analysis \n```python\n{\n \"tool\": \"correlation_analysis\",\n \"args\": {\n \"data\": {\n \"x\": [1, 2, 3, 4, 5],\n \"y\": [2, 4, 6, 8, 10]\n },\n \"variables\": [\"x\", \"y\"],\n \"method\": \"pearson\"\n }\n}\n```\n\n#### Logistic Regression\n```python\n{\n \"tool\": \"logistic_regression\", \n \"args\": {\n \"formula\": \"churn ~ tenure_months + monthly_charges\",\n \"data\": {\n \"churn\": [0, 1, 0, 1],\n \"tenure_months\": [24, 6, 36, 3], \n \"monthly_charges\": [70, 85, 65, 90]\n },\n \"family\": \"binomial\",\n \"link\": \"logit\"\n }\n}\n```\n\n## \ud83e\uddea Testing & Validation\n\nRMCP includes comprehensive testing with realistic scenarios:\n\n```bash\n# Run all user scenarios (should show 100% pass rate)\npython tests/realistic_scenarios.py\n\n# Run development test script\nbash src/rmcp/scripts/test.sh\n```\n\n**Current Test Coverage**: \n- \u2705 **MCP Interface**: 100% success rate (5/5 tests) - Validates actual Claude Desktop integration\n- \u2705 **User Scenarios**: 100% success rate (4/4 tests) - Validates real-world usage patterns\n- \u2705 **Conversational Examples**: All documented examples tested and verified working\n\n## \ud83c\udfd7\ufe0f Architecture\n\nRMCP is built with production best practices:\n\n- **Clean Architecture**: Modular design with clear separation of concerns\n- **MCP Compliance**: Full Model Context Protocol specification support\n- **Transport Layer**: Pluggable transports (stdio, HTTP, WebSocket)\n- **R Integration**: Safe subprocess execution with JSON serialization\n- **Error Handling**: Comprehensive error reporting and recovery\n- **Security**: Controlled R execution environment\n\n```\nsrc/rmcp/\n\u251c\u2500\u2500 core/ # MCP server core\n\u251c\u2500\u2500 tools/ # Statistical analysis tools \n\u251c\u2500\u2500 transport/ # Communication layers\n\u251c\u2500\u2500 registries/ # Tool and resource management\n\u2514\u2500\u2500 security/ # Safe execution environment\n```\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions! Please see our [contributing guidelines](CONTRIBUTING.md).\n\n### Development Setup\n```bash\ngit clone https://github.com/gojiplus/rmcp.git\ncd rmcp\npip install -e \".[dev]\"\npre-commit install\n```\n\n### Running Tests\n```bash\npython tests/realistic_scenarios.py # User scenarios\npytest tests/ # Unit tests (if any)\n```\n\n## \ud83d\udcc4 License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n## \ud83d\ude4b Support\n\n- \ud83d\udcd6 **Documentation**: See [Quick Start Guide](examples/quick_start_guide.md) for working examples\n- \ud83d\udc1b **Issues**: [GitHub Issues](https://github.com/gojiplus/rmcp/issues)\n- \ud83d\udcac **Discussions**: [GitHub Discussions](https://github.com/gojiplus/rmcp/discussions)\n\n## \ud83c\udf89 Acknowledgments\n\nRMCP builds on the excellent work of:\n- [Model Context Protocol](https://modelcontextprotocol.io/) specification\n- [R Project](https://www.r-project.org/) statistical computing environment\n- The broader open-source statistical computing community\n\n---\n\n**Ready to analyze data like never before?** Install RMCP and start running sophisticated statistical analyses through AI assistants today! \ud83d\ude80\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Comprehensive Model Context Protocol server with 33 statistical analysis tools across 8 categories",
"version": "0.3.2",
"project_urls": {
"Documentation": "https://github.com/gojiplus/rmcp#readme",
"Homepage": "https://github.com/gojiplus/rmcp",
"Issues": "https://github.com/gojiplus/rmcp/issues",
"Repository": "https://github.com/gojiplus/rmcp"
},
"split_keywords": [
"mcp",
" r",
" statistics",
" econometrics",
" model-context-protocol",
" data-analysis"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "2f45861ebe94e5dad8cb722ff451227410b7c44af4eff262a9ea01695e9f1204",
"md5": "1cf13072b013edcef53fd4c77ff94b4a",
"sha256": "aa1250c5ad32f8883fdaff6f79d1ef43f5b1c40ac473fc58b624b75aeb96eaa4"
},
"downloads": -1,
"filename": "rmcp-0.3.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1cf13072b013edcef53fd4c77ff94b4a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 58763,
"upload_time": "2025-08-30T20:58:22",
"upload_time_iso_8601": "2025-08-30T20:58:22.358990Z",
"url": "https://files.pythonhosted.org/packages/2f/45/861ebe94e5dad8cb722ff451227410b7c44af4eff262a9ea01695e9f1204/rmcp-0.3.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7b88ab27c67ee6886b33531d07b106f46aede09b4cfb404d9c7672ec31554b7a",
"md5": "cecf17ec8b8d58f5af452db8ac4ca030",
"sha256": "35b63105a8e8b91c6d3bcbad0e46a720ae96f429611dfd08b73bc967e0ec5fcb"
},
"downloads": -1,
"filename": "rmcp-0.3.2.tar.gz",
"has_sig": false,
"md5_digest": "cecf17ec8b8d58f5af452db8ac4ca030",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 59795,
"upload_time": "2025-08-30T20:58:23",
"upload_time_iso_8601": "2025-08-30T20:58:23.800165Z",
"url": "https://files.pythonhosted.org/packages/7b/88/ab27c67ee6886b33531d07b106f46aede09b4cfb404d9c7672ec31554b7a/rmcp-0.3.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-30 20:58:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "gojiplus",
"github_project": "rmcp#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "click",
"specs": [
[
">=",
"8.1.0"
]
]
},
{
"name": "jsonschema",
"specs": [
[
">=",
"4.0.0"
]
]
}
],
"lcname": "rmcp"
}
JSON
