> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memoryo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# MemoryOS MCP Server

> Run MemoryOS as a sidecar tool server for AI agents, IDEs, and local assistants.

MemoryOS MCP lets an agent call MemoryOS as tools instead of importing the SDK directly into the main application process.

Use MCP when you want MemoryOS isolated from your core backend, or when your agent runtime already supports the Model Context Protocol.

<img src="https://mintcdn.com/memoryengine/6B03i3-oAOTaxCpG/images/api-key-settings-placeholder.svg?fit=max&auto=format&n=6B03i3-oAOTaxCpG&q=85&s=b59f1ba1d29fca98a6d7168278b45788" alt="Placeholder: create a MemoryOS API key from the workspace dashboard" width="1200" height="760" data-path="images/api-key-settings-placeholder.svg" />

## Install

```bash theme={null}
pip install memoryos-mcp
```

For local development from this repository:

```bash theme={null}
cd memoryos-mcp
pip install -e .
```

## Configure

Use a workspace API key from the MemoryOS dashboard.

```bash theme={null}
MEMORYOS_API_KEY=mem_live_xxx
MEMORYOS_API_URL=https://api.memoryos.io
```

For local Docker:

```bash theme={null}
MEMORYOS_API_URL=http://localhost:8000
```

## Run

```bash theme={null}
memoryos-mcp
```

Claude Desktop example:

```json theme={null}
{
  "mcpServers": {
    "memoryos": {
      "command": "memoryos-mcp",
      "env": {
        "MEMORYOS_API_KEY": "mem_live_xxx",
        "MEMORYOS_API_URL": "https://api.memoryos.io"
      }
    }
  }
}
```

## What the agent can call

The MCP server exposes first-class tools for the normal MemoryOS flow:

```text theme={null}
memoryos_add_memory
memoryos_get_context
memoryos_list_memories
memoryos_delete_memory
memoryos_get_job_status
```

It also exposes domain and cross-agent tools:

```text theme={null}
memoryos_get_domain_schema
memoryos_set_domain_schema
memoryos_get_edtech_profile
memoryos_set_support_type
memoryos_list_support_customers
memoryos_get_support_stats
memoryos_create_consent_url
memoryos_universal_get_context
memoryos_universal_add_memory
```

For newly released endpoints, `memoryos_api_request` provides an allowlisted escape hatch across MemoryOS API paths.

## One server for every schema

You do not run separate MCP servers for General, EdTech, and Customer Support.

The tool call stays the same:

```json theme={null}
{
  "external_user_id": "cust_123",
  "query": "what should I know before replying?"
}
```

MemoryOS applies the correct engine based on your workspace setting:

```text theme={null}
General Engine -> general memory context
EdTech Schema -> general context + tutoring profile
Customer Support Schema -> general context + support profile
```

## Support agent boundary

For customer support, MCP gives the agent remembered context. Your support platform still provides live tools.

```text theme={null}
MemoryOS MCP:
  what does this customer prefer?
  what open issue did they mention earlier?
  what context should the agent not ask again?

Your backend tools:
  get_order()
  create_refund()
  get_invoice()
  update_ticket()
```

The agent should not claim a refund, invoice, or account change was completed unless your own backend tool actually completed it.