---
title: Evolva Codebase Memory MCP
emoji: 🧠
colorFrom: blue
colorTo: purple
sdk: docker
pinned: true
license: mit
app_port: 7860
---

# Evolva Codebase Memory MCP Server

> MCP server providing codebase memory and knowledge graph access for **54 Evolva repositories** across a **7-layer architecture**.

## Overview

This MCP (Model Context Protocol) server indexes the entire Evolva codebase and exposes it through 6 powerful tools that any AI agent can use to understand the codebase structure, dependencies, and relationships.

## API Endpoints

| Endpoint | Description |
|----------|-------------|
| `GET /health` | Health check — returns `{"status": "up", "repos_indexed": 54}` |
| `GET /mcp/tools` | Returns all 6 MCP tool definitions |
| `POST /mcp/call` | Execute an MCP tool call |
| `GET /v1/repos` | List all 54 repositories |
| `GET /v1/repos/{name}` | Get details for a specific repo |
| `GET /v1/architecture` | Get the 7-layer architecture |
| `GET /v1/stats` | Get aggregate statistics |
| `GET /v1/relationships` | Get all dependency relationships |
| `GET /docs` | Documentation site |

## 6 MCP Tools

1. **search_repos** — Search repositories by name, topic, language, or layer
2. **get_repo_details** — Get detailed info about a specific repository
3. **get_architecture** — Get the full 7-layer architecture overview
4. **get_dependencies** — Get dependency graph for a repository
5. **get_stats** — Get aggregate codebase statistics
6. **find_related** — Find repositories related to a given repo

## 7-Layer Architecture

| Layer | Name | Repos |
|-------|------|-------|
| 1 | Foundation & Infrastructure | 7 |
| 2 | Data & Storage Layer | 7 |
| 3 | AI & ML Core | 7 |
| 4 | Agent Framework | 7 |
| 5 | MCP & Integration Layer | 9 |
| 6 | Applications & Services | 7 |
| 7 | Research & Experimental | 8 |

## Usage with MCP

```json
{
  "mcpServers": {
    "evolva-codebase-memory": {
      "url": "https://pippinlitli-evolva-codebase-memory.hf.space/mcp",
      "transport": "http"
    }
  }
}
```

## License

MIT © Evolva Team