---
title: 'MCP Server Installation'
description: 'Install and configure the T6 Mem0 v2 MCP server'
---

# Installing the MCP Server

The MCP server can be run in two modes: HTTP/SSE for web integrations, or stdio for local tool usage.

## Prerequisites

- Python 3.11+
- Running Supabase instance (vector store)
- Running Neo4j instance (graph store)
- OpenAI API key

## Environment Setup

Create a `.env` file with required configuration:

```bash
# OpenAI
OPENAI_API_KEY=your_openai_key_here

# Supabase (Vector Store)
SUPABASE_CONNECTION_STRING=postgresql://user:pass@host:port/database

# Neo4j (Graph Store)
NEO4J_URI=neo4j://localhost:7687
NEO4J_USER=neo4j
NEO4J_PASSWORD=your_neo4j_password

# MCP Server
MCP_HOST=0.0.0.0
MCP_PORT=8765

# Mem0 Configuration
MEM0_COLLECTION_NAME=t6_memories
MEM0_EMBEDDING_DIMS=1536
MEM0_VERSION=v1.1
```

## Installation Methods

### Method 1: Docker (Recommended)

The easiest way to run the MCP server is using Docker Compose:

```bash
# Clone the repository
git clone https://git.colsys.tech/klas/t6_mem0_v2
cd t6_mem0_v2

# Copy and configure environment
cp .env.example .env
# Edit .env with your settings

# Start all services
docker compose up -d

# MCP HTTP server will be available at http://localhost:8765
```

**Health Check**:
```bash
curl http://localhost:8765/health
# {"status":"healthy","service":"t6-mem0-v2-mcp-http","transport":"http-streamable"}
```

### Method 2: Local Python

For development or local usage:

```bash
# Install dependencies
pip install -r requirements.txt

# Run HTTP server
python -m mcp_server.http_server

# Or run stdio server (for Claude Code)
python -m mcp_server.main
```

## Verify Installation

### Test HTTP Endpoint

```bash
curl -X POST "http://localhost:8765/mcp" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/list",
    "params": {}
  }'
```

Expected response:
```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "tools": [
      {
        "name": "add_memory",
        "description": "Add new memory from messages...",
        "inputSchema": {...}
      },
      // ... 6 more tools
    ]
  }
}
```

### Test stdio Server

```bash
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | python -m mcp_server.main
```

## Docker Configuration

The MCP server is configured in `docker-compose.yml`:

```yaml
mcp-server:
  build:
    context: .
    dockerfile: docker/Dockerfile.mcp
  container_name: t6-mem0-mcp
  restart: unless-stopped
  ports:
    - "8765:8765"
  environment:
    - OPENAI_API_KEY=${OPENAI_API_KEY}
    - SUPABASE_CONNECTION_STRING=${SUPABASE_CONNECTION_STRING}
    - NEO4J_URI=neo4j://neo4j:7687
    - NEO4J_USER=${NEO4J_USER}
    - NEO4J_PASSWORD=${NEO4J_PASSWORD}
    - MCP_HOST=0.0.0.0
    - MCP_PORT=8765
  depends_on:
    neo4j:
      condition: service_healthy
  networks:
    - localai
  healthcheck:
    test: ["CMD-SHELL", "curl -f http://localhost:8765/health || exit 1"]
    interval: 30s
    timeout: 10s
    retries: 3
```

## Network Configuration

For n8n integration on the same Docker network:

```yaml
# Add to your n8n docker-compose.yml
networks:
  localai:
    external: true

services:
  n8n:
    networks:
      - localai
```

Then use internal Docker network IP in n8n:
```
http://172.21.0.14:8765/mcp
```

Find the MCP container IP:
```bash
docker inspect t6-mem0-mcp --format='{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}'
```

## Troubleshooting

### Container Won't Start

Check logs:
```bash
docker logs t6-mem0-mcp --tail 50
```

Common issues:
- Missing environment variables
- Cannot connect to Neo4j or Supabase
- Port 8765 already in use

### Health Check Failing

Verify services are reachable:
```bash
# Test Neo4j connection
docker exec t6-mem0-mcp curl http://neo4j:7474

# Test from host
curl http://localhost:8765/health
```

### n8n Can't Connect

1. Verify same Docker network:
   ```bash
   docker network inspect localai
   ```

2. Test connectivity from n8n container:
   ```bash
   docker run --rm --network localai alpine/curl:latest \
     curl -s http://172.21.0.14:8765/health
   ```

## Next Steps

<CardGroup cols={2}>
  <Card title="Tool Reference" icon="wrench" href="/mcp/tools">
    Learn about available MCP tools
  </Card>
  <Card title="n8n Integration" icon="workflow" href="/examples/n8n">
    Use MCP in n8n workflows
  </Card>
</CardGroup>