
Axon.MCP.Server
by ali-kamali·★ 165·Score 50
MCP server that transforms codebases into intelligent knowledge bases for AI IDEs like Cursor and AntiGravity with semantic analysis and vector search.
Overview
Axon.MCP.Server is a comprehensive Model Context Protocol implementation that enables AI assistants to deeply understand codebases beyond simple syntax parsing. It combines Tree-sitter for multi-language syntax analysis with Roslyn for C# semantic understanding, creating detailed call graphs, inheritance hierarchies, and dependency networks. The system uses vector embeddings for semantic code search and can automatically detect services, APIs, Entity Framework mappings, and design patterns. It features a 10-service microarchitecture with production-grade observability through Prometheus and Grafana dashboards, along with enterprise security features including JWT authentication and RBAC.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
Choose Axon when you need deep semantic understanding of your C# or Python codebase for AI-powered development in Cursor or other MCP-enabled IDEs.
When NOT to choose this
Not suitable if you need multi-language support beyond C# and Python, or if you prefer a lightweight solution without the overhead of its full microservice architecture.
Tools this server exposes
12 tools extracted from the READMEsearchSemantic + full-text code search
get_call_graphFunction call relationships
get_inheritance_hierarchyClass inheritance tree
get_api_endpointsList REST API routes
get_ef_entitiesEntity Framework mappings
get_module_summaryAI-generated code summaries
explore_serviceNavigate service architecture
find_implementationsInterface implementations
get_system_architecture_mapGenerate architecture diagrams
get_symbol_detailsDetailed symbol info
get_file_symbolsList symbols in a file
get_repository_structureProject/solution organization
Comparable tools
Installation
Quick Start with Docker
# Clone the repository
git clone https://github.com/ali-kamali/Axon.MCP.Server.git
cd axon.mcp.server
# Copy environment template
cp .env.example .env
# Edit .env with your credentials
# Set GITLAB_TOKEN or AZUREDEVOPS_PASSWORD
# Set ADMIN_API_KEY and ADMIN_PASSWORD
# Start all services
make docker-up
# Run database migrations
make migrateClaude Desktop Configuration
Add to claude_desktop_config.json:
{
"mcpServers": {
"axon": {
"command": "python",
"args": ["-m", "uvicorn", "axon_mcp_server.main:app", "--host", "0.0.0.0", "--port", "8001"],
"env": {
"AXON_ADMIN_API_KEY": "your-api-key"
}
}
}
}FAQ
- What programming languages does Axon support?
- Axon supports deep analysis for C# (with Roslyn), Python, JavaScript, and TypeScript. It can parse other languages with Tree-sitter but provides more detailed analysis for the primary four.
- How does Axon handle large codebases?
- Axon is designed for performance with <500ms p95 latency and can handle 10,000+ files. It uses smart caching, parallel processing with Celery workers, and PostgreSQL with pgvector for efficient storage and retrieval.
Compare Axon.MCP.Server with
Last updated · Auto-generated from public README + GitHub signals.