Documentation Index
Fetch the complete documentation index at: https://mintlify.com/poweroutlet2/openground/llms.txt
Use this file to discover all available pages before exploring further.
Overview
The OpenGround MCP server can be customized through configuration files, environment variables, and runtime settings. This guide covers all configuration options and best practices.Configuration File
Location
OpenGround uses a JSON configuration file located at: Linux/macOS:Structure
Configuration Options
Database Settings
Path to the LanceDB database directory. All documentation vectors and metadata are stored here.Example:
"/Users/john/.local/share/openground/lancedb"Name of the LanceDB table containing documentation chunks.Example:
"documents", "docs_v2"Base directory for storing raw downloaded documentation HTML/markdown files.Example:
"/Users/john/.local/share/openground/raw_data"Extraction Settings
Maximum number of concurrent HTTP requests when downloading documentation.Range: 1-200
Recommended: 20-100 depending on network bandwidth
Recommended: 20-100 depending on network bandwidth
Embedding Settings
Number of text chunks to process in a single embedding batch.Range: 1-128
Memory impact: Higher = more memory usage
Speed impact: Higher = faster processing
Memory impact: Higher = more memory usage
Speed impact: Higher = faster processing
Maximum number of characters per documentation chunk.Range: 200-2000
Recommended: 600-1000 for balanced context
Recommended: 600-1000 for balanced context
Number of overlapping characters between adjacent chunks.Range: 0-500
Purpose: Ensures context continuity across chunk boundaries
Purpose: Ensures context continuity across chunk boundaries
Hugging Face model identifier for generating embeddings.Popular options:
"BAAI/bge-small-en-v1.5"- Fast, 384 dimensions (default)"BAAI/bge-base-en-v1.5"- Balanced, 768 dimensions"BAAI/bge-large-en-v1.5"- Highest quality, 1024 dimensions
Dimensionality of the embedding vectors. Must match the model’s output dimension.Model dimensions:
- BGE-small: 384
- BGE-base: 768
- BGE-large: 1024
Backend library for generating embeddings.Options:
"fastembed"- Fast, optimized for CPU (default)"sentence-transformers"- More models, GPU support
Query Settings
Number of search results returned by
Recommended: 3-10 for most use cases
search_documents_tool.Range: 1-100Recommended: 3-10 for most use cases
Source Settings
Automatically detect and add project-local source definitions.Purpose: Enables project-specific documentation sources via
.openground/sources.jsonEnvironment Variables
System Environment
These environment variables are set automatically by the MCP server at startup:Disables tokenizer parallelism to prevent stdout pollution.Purpose: Ensures clean JSON-RPC communication with MCP clients
Reduces transformers library logging to errors only.Purpose: Prevents debug logs from interfering with MCP protocol
Suppresses fastembed transformers logging.Purpose: Clean server output
User Environment Variables
You can set these before running the MCP server:Overrides the default config directory location.Example:
Result: Config file at
export XDG_CONFIG_HOME=/custom/configResult: Config file at
/custom/config/openground/config.jsonOverrides the default data directory location.Example:
Result: Database at
export XDG_DATA_HOME=/custom/dataResult: Database at
/custom/data/openground/lancedbMCP Server Configuration
FastMCP Settings
The server is built using FastMCP with these settings:Server Startup Process
- Environment setup: Set silence environment variables
- Background initialization: Start daemon thread to pre-load resources
- Cache warming: Load library metadata and embedding model
- MCP transport: Initialize stdio transport
- Ready signal: Log “Server is fully ready” message
Pre-loading Behavior
The server pre-loads resources in a background thread:- First tool call is instant (no cold start)
- Embedding model is in memory
- Library metadata is cached
- Number of libraries in database
- Embedding model size
- Disk I/O speed
Managing Configuration
View Current Config
Set Individual Values
Reset to Defaults
Edit Manually
Performance Tuning
For Fast Search (Low Latency)
- Search: < 100ms
- Model size: ~90MB
- Memory usage: ~200MB
For High Accuracy (Better Results)
- Search: 200-500ms
- Model size: ~1.3GB
- Memory usage: ~2GB
- Better semantic understanding
For Large Documentation Sets
- Faster ingestion
- Smaller chunks = more granular search
- Higher batch size = faster embedding
For Memory-Constrained Systems
- Lower memory footprint
- Slower processing
- Still good search quality
Advanced Configuration
Custom Database Location
Move database to SSD for better performance:Multiple Environments
Use different configs for development vs. production: Development:Project-Local Sources
Create project-specific documentation sources:.openground/sources.json:
sources.auto_add_local: true, this source is automatically available when working in this directory.
Troubleshooting
Config File Not Found
Symptom: Server uses all defaults Solution: Create config file:Invalid JSON
Error:Invalid JSON in config file
Solution: Validate JSON syntax:
Changes Not Taking Effect
Symptom: Modified config but server still uses old values Solution: Configuration is cached at server startup. Restart your MCP client to reload the server with new config.Database Path Issues
Error:Database not found or Table doesn't exist
Solution: Verify paths are correct and accessible:
Embedding Model Download Fails
Symptom: Server hangs or errors during initialization Solution:- Check internet connection
- Manually download model:
- Use alternative model:
Best Practices
Configuration Checklist
- Config file is valid JSON
-
db_pathpoints to accessible directory -
embedding_dimensionsmatchesembedding_model -
chunk_size>chunk_overlap -
top_kis reasonable (3-20) -
concurrency_limitdoesn’t overwhelm network - Environment variables don’t conflict
- Server restarts after config changes
Next Steps
Search Documents
Learn how to effectively search documentation with your configured server
List Libraries
Understand available libraries and versions