Sumo Logic MCP Server
Enables interaction with Sumo Logic's REST APIs through MCP, allowing log search, dashboard management, metrics querying, collector and monitor operations.
README
Sumo Logic MCP Python Server
A Python implementation of a Model Context Protocol (MCP) server for Sumo Logic API integration. This server provides a comprehensive interface to Sumo Logic's REST APIs through the MCP protocol, enabling seamless integration with MCP-compatible clients.
Features
This MCP server provides tools to interact with Sumo Logic's APIs, allowing users to:
🔍 Search & Analytics
- Execute log search queries with flexible parameters
- Monitor search job status and retrieve results
- Support for pagination and result limiting
📊 Dashboard Management
- List, create, update, and delete dashboards
- Retrieve dashboard configurations and metadata
- Manage dashboard panels and visualizations
📈 Metrics & Monitoring
- Query time-series metrics data
- Support for metric selectors and aggregations
- List available metric sources
🔧 Collector & Source Management
- Manage collectors (list, create, update, delete)
- Configure data sources within collectors
- Monitor collector status and health
🚨 Monitor Management
- Create, update, and delete monitoring rules
- List and search monitors with advanced filtering
- Enable/disable monitors and manage their status
- Get active alerts and monitor health status
- Validate monitor configurations
- View monitor execution history and performance metrics
Requirements
- Python 3.8 or higher
- Sumo Logic account with API access
- Valid Sumo Logic Access ID and Access Key
Installation
From PyPI (published)
pip install sumologic-mcp-python
From Source
- Clone the repository:
git clone https://github.com/sumologic/sumologic-mcp-python.git
cd sumologic-mcp-python
- Install the package:
pip install -e .
Development Installation
For development with all dependencies:
pip install -e ".[dev]"
Configuration
The Sumo Logic MCP Server supports multiple configuration methods with comprehensive validation and clear error messages.
Configuration Methods
The server supports configuration through multiple sources with the following precedence (highest to lowest):
- Command-line arguments (highest precedence)
- Environment variables
- Configuration file
- Default values (lowest precedence)
Environment Variables
Configure the server using environment variables with the SUMOLOGIC_ prefix:
| Variable | Required | Default | Description | Valid Values |
|---|---|---|---|---|
SUMOLOGIC_ACCESS_ID |
✅ | - | Your Sumo Logic Access ID | 14 alphanumeric characters |
SUMOLOGIC_ACCESS_KEY |
✅ | - | Your Sumo Logic Access Key | At least 20 characters |
SUMOLOGIC_ENDPOINT |
✅ | - | Sumo Logic API endpoint | Valid HTTPS URL ending in .sumologic.com |
SUMOLOGIC_TIMEOUT |
❌ | 30 | Request timeout in seconds | 1-300 |
SUMOLOGIC_MAX_RETRIES |
❌ | 3 | Maximum retry attempts | 0-10 |
SUMOLOGIC_RATE_LIMIT_DELAY |
❌ | 1.0 | Delay between rate-limited requests | 0.1-60.0 |
SUMOLOGIC_LOG_LEVEL |
❌ | INFO | Log level | DEBUG, INFO, WARNING, ERROR, CRITICAL |
SUMOLOGIC_LOG_FORMAT |
❌ | json | Log format | json, text |
SUMOLOGIC_SERVER_NAME |
❌ | sumologic-mcp-server | MCP server name | Any string |
SUMOLOGIC_SERVER_VERSION |
❌ | 0.1.1 | MCP server version | Any string |
Configuration File Support
Create a JSON configuration file for easier management:
Minimal Configuration (config.json):
{
"access_id": "your_access_id_here",
"access_key": "your_access_key_here",
"endpoint": "https://api.sumologic.com"
}
Full Configuration (config.json):
{
"access_id": "your_access_id_here",
"access_key": "your_access_key_here",
"endpoint": "https://api.sumologic.com",
"timeout": 30,
"max_retries": 3,
"rate_limit_delay": 1.0,
"log_level": "INFO",
"log_format": "json",
"server_name": "sumologic-mcp-server",
"server_version": "0.1.1"
}
Use the configuration file:
sumologic-mcp-server --config-file config.json
Configuration Validation
The server includes comprehensive configuration validation with detailed error messages and recommendations.
Validate Configuration:
# Validate current environment configuration
sumologic-mcp-server --validate-config
# Validate specific configuration file
sumologic-mcp-server --config-file config.json --validate-config
Example Validation Output:
============================================================
SUMO LOGIC MCP SERVER - CONFIGURATION VALIDATION
============================================================
Configuration Sources:
🌍 Environment variables: SUMOLOGIC_ACCESS_ID, SUMOLOGIC_ACCESS_KEY, SUMOLOGIC_ENDPOINT
⚙️ Using defaults for: timeout, max_retries, rate_limit_delay, log_level
Current Configuration:
Access ID: ✓ (configured)
Access Key: ✓ (configured)
Endpoint: ✓ https://api.sumologic.com
Timeout: 30s
Max Retries: 3
Rate Limit Delay: 1.0s
Log Level: INFO
Log Format: json
⚠️ CONFIGURATION WARNINGS:
• timeout: Timeout of 5s is quite low and may cause request failures
💡 Recommendation: Consider using a timeout of at least 10 seconds
✅ CONFIGURATION IS VALID - Server can start
============================================================
Setup Instructions
-
Get Sumo Logic Credentials:
- Log into your Sumo Logic account
- Go to Administration > Security > Access Keys
- Create a new Access Key or use existing credentials
-
Choose Configuration Method:
Option A: Environment Variables
export SUMOLOGIC_ACCESS_ID="your_access_id_here" export SUMOLOGIC_ACCESS_KEY="your_access_key_here" export SUMOLOGIC_ENDPOINT="https://api.sumologic.com"Option B: .env File
# Copy example file cp .env.example .env # Edit with your credentials nano .envOption C: Configuration File
# Create config.json (see examples above) # Use with: sumologic-mcp-server --config-file config.json -
Validate Configuration:
sumologic-mcp-server --validate-config -
Start Server:
sumologic-mcp-server
Configuration Examples
Development Setup:
export SUMOLOGIC_LOG_LEVEL=DEBUG
export SUMOLOGIC_LOG_FORMAT=text
export SUMOLOGIC_TIMEOUT=60
sumologic-mcp-server
Production Setup:
{
"access_id": "your_access_id",
"access_key": "your_access_key",
"endpoint": "https://api.sumologic.com",
"timeout": 45,
"max_retries": 5,
"rate_limit_delay": 1.5,
"log_level": "WARNING",
"log_format": "json"
}
High-Volume Environment:
export SUMOLOGIC_TIMEOUT=60
export SUMOLOGIC_MAX_RETRIES=5
export SUMOLOGIC_RATE_LIMIT_DELAY=0.5
export SUMOLOGIC_LOG_LEVEL=WARNING
Configuration Troubleshooting
Common Configuration Errors:
-
Missing Required Credentials:
❌ access_id: Sumo Logic Access ID is required. Set SUMOLOGIC_ACCESS_ID environment variable.Solution: Set the required environment variables or add them to your config file.
-
Invalid Endpoint Format:
❌ endpoint: Endpoint must be a valid Sumo Logic domainSolution: Use a valid Sumo Logic endpoint (e.g.,
https://api.sumologic.com). -
Invalid Access ID Format:
❌ access_id: Access ID must be 14 alphanumeric charactersSolution: Verify your Access ID is exactly 14 characters.
-
Configuration File Issues:
❌ Configuration file error: Invalid JSON in configuration fileSolution: Validate your JSON syntax using a JSON validator.
For detailed configuration documentation, see docs/configuration.md.
Usage
Starting the Server
Basic Usage:
sumologic-mcp-server
With Custom Log Level:
SUMOLOGIC_LOG_LEVEL=DEBUG sumologic-mcp-server
With Text Logging:
sumologic-mcp-server --log-format text
Validate Configuration Only:
sumologic-mcp-server --validate-config
Command Line Options
sumologic-mcp-server --help
Available options:
--config-file PATH: Path to configuration file (optional)--validate-config: Validate configuration and exit--log-level LEVEL: Override log level (DEBUG, INFO, WARNING, ERROR, CRITICAL)--log-format FORMAT: Override log format (json, text)--version: Show version information
Running as Python Module
python -m sumologic_mcp
MCP Client Integration
Configure your MCP client to connect to this server. Example configuration for various clients:
Claude Desktop (config.json):
{
"mcpServers": {
"sumologic": {
"command": "sumologic-mcp-server",
"env": {
"SUMOLOGIC_ACCESS_ID": "your_access_id",
"SUMOLOGIC_ACCESS_KEY": "your_access_key",
"SUMOLOGIC_ENDPOINT": "https://api.sumologic.com"
}
}
}
}
Available Tools
Search Tools
search_logs: Execute log search queriesget_search_job_status: Check search job statusget_search_results: Retrieve search results with pagination
Dashboard Tools
list_dashboards: List all dashboardsget_dashboard: Get specific dashboard detailscreate_dashboard: Create new dashboardupdate_dashboard: Update existing dashboarddelete_dashboard: Delete dashboard
Metrics Tools
query_metrics: Execute metrics querieslist_metric_sources: List available metric sources
Collector Tools
list_collectors: List all collectorsget_collector: Get collector detailscreate_collector: Create new collectorupdate_collector: Update collector configurationdelete_collector: Delete collectorlist_sources: List sources in collectorcreate_source: Create new source
Monitor Tools
list_monitors: List all monitors with filtering and paginationsearch_monitors: Search monitors with advanced query capabilitiesget_monitor: Get detailed monitor configuration and metadatacreate_monitor: Create new monitor with validationupdate_monitor: Update existing monitor configurationdelete_monitor: Delete monitor with cascade informationget_monitor_status: Get current monitor status and healthget_active_alerts: Get all currently active alertsenable_monitor: Enable specified monitordisable_monitor: Disable specified monitorvalidate_monitor_config: Validate monitor configurationget_monitor_history: Get monitor execution history and metrics
Development
Setup Development Environment
-
Clone and Install:
git clone https://github.com/sumologic/sumologic-mcp-python.git cd sumologic-mcp-python pip install -e ".[dev]" -
Install Pre-commit Hooks:
pre-commit install
Development Commands
Run Tests:
# All tests
pytest
# Unit tests only
pytest -m unit
# Integration tests only
pytest -m integration
# With coverage
pytest --cov=sumologic_mcp --cov-report=html
Code Formatting:
# Format code
black sumologic_mcp/ tests/
isort sumologic_mcp/ tests/
# Check formatting
black --check sumologic_mcp/ tests/
isort --check-only sumologic_mcp/ tests/
Type Checking:
mypy sumologic_mcp/
Linting:
flake8 sumologic_mcp/ tests/
Run All Checks:
pre-commit run --all-files
Project Structure
sumologic-mcp-python/
├── sumologic_mcp/ # Main package
│ ├── __init__.py
│ ├── main.py # Entry point
│ ├── server.py # MCP server implementation
│ ├── config.py # Configuration management
│ ├── auth.py # Authentication
│ ├── api_client.py # Sumo Logic API client
│ ├── error_handler.py # Error handling
│ ├── exceptions/ # Custom exceptions
│ ├── models/ # Data models
│ └── tools/ # MCP tool implementations
├── tests/ # Test suite
├── .env.example # Example environment file
├── pyproject.toml # Project configuration
├── README.md # This file
└── LICENSE # License file
Troubleshooting
Common Issues
Authentication Errors:
- Verify your Access ID and Access Key are correct
- Ensure your endpoint URL is correct for your Sumo Logic deployment
- Check that your credentials have necessary permissions
Connection Issues:
- Verify network connectivity to Sumo Logic endpoints
- Check firewall settings
- Ensure proper SSL/TLS configuration
Rate Limiting:
- The server automatically handles rate limiting with exponential backoff
- Adjust
SUMOLOGIC_RATE_LIMIT_DELAYif needed - Monitor logs for rate limit warnings
Debug Mode
Enable debug logging for detailed troubleshooting:
SUMOLOGIC_LOG_LEVEL=DEBUG sumologic-mcp-server --log-format text
Getting Help
- Check the Issues page
- Review Sumo Logic API documentation
- Enable debug logging for detailed error information
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Ensure all tests pass and code is formatted
- Submit a pull request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Built on the Model Context Protocol specification
- Integrates with Sumo Logic APIs
- Inspired by the TypeScript implementation at mcp-sumologic
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。