Model Context Protocol server providing AI agents with deep knowledge of the Evolva codebase — 54 repositories, 7 architecture layers, full dependency graph.
Every tool is callable via the MCP protocol or directly via REST POST to /mcp/call.
Search repositories by name, topic, language, or architecture layer with relevance scoring.
Get detailed information about a specific repository including all metadata and dependency relationships.
Get the full 7-layer architecture overview with all repositories organized by layer.
Get the dependency graph for a repository — what it depends on (upstream) and what depends on it (downstream).
Get aggregate statistics: language distribution, layer sizes, star counts, and topic frequency analysis.
Find repositories related to a given repo based on shared topics, language, layer proximity, or dependency graph.
54 repositories organized into 7 logical layers from infrastructure to research.
Core infrastructure, DevOps, CI/CD, containerization, and base platform services
Databases, vector stores, knowledge graphs, and data persistence systems
Machine learning models, training pipelines, inference engines, and AI primitives
Agent orchestration, multi-agent systems, memory management, and tool use
Model Context Protocol servers, API integrations, and connector ecosystem
End-user applications, web services, dashboards, and product interfaces
Research projects, experimental features, prototypes, and innovation lab
All endpoints are available at the Hugging Face Space URL.
| Method | Endpoint | Description |
|---|---|---|
| GET | /health | Health check — returns status and repos_indexed count |
| GET | /mcp/tools | List all 6 MCP tool definitions |
| POST | /mcp/call | Execute an MCP tool call with JSON body |
| GET | /v1/repos | List all 54 repositories (supports ?layer, ?language, ?topic filters) |
| GET | /v1/repos/{name} | Get details for a specific repository |
| GET | /v1/architecture | Get the 7-layer architecture (supports ?layer_id filter) |
| GET | /v1/stats | Get aggregate codebase statistics |
| GET | /v1/relationships | Get all dependency relationships |
| GET | /docs | This documentation site |
| GET | /api/docs | Interactive Swagger UI |
Connect to the MCP server or call the REST API directly.
{
"mcpServers": {
"evolva-codebase-memory": {
"url": "https://pippinlitli-evolva-codebase-memory.hf.space",
"transport": "http"
}
}
}import requests BASE = "https://pippinlitli-evolva-codebase-memory.hf.space" # Search for agent-related repos resp = requests.post(f"{BASE}/mcp/call", json={ "name": "search_repos", "arguments": {"query": "agent", "layer": 4} }) print(resp.json()) # Get architecture overview arch = requests.get(f"{BASE}/v1/architecture").json() print(f"Layers: {arch['total_layers']}, Repos: {arch['total_repos']}")
curl https://pippinlitli-evolva-codebase-memory.hf.space/health # {"status":"up","repos_indexed":54,"version":"1.0.0","layers":7} curl https://pippinlitli-evolva-codebase-memory.hf.space/mcp/tools | jq '.count' # 6