# memory_read_graph

Read and retrieve the entire user

Agent View of the PolicyLayer registry record for `memory_read_graph`. HTML page: https://policylayer.com/tools/3xcaffeine-mcp-server/memory-read-graph

## Facts

- Tool: `memory_read_graph`
- Server: VaultAssist (`3xcaffeine/mcp-server`) — https://policylayer.com/tools/3xcaffeine-mcp-server.md
- Homepage: https://github.com/3xcaffeine/mcp-server
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "memory_read_graph",
    "arguments": {}
  }
}
```

## Why memory_read_graph is rated Low

The tool is a Read operation that accesses user data at scale ('entire user'). While it has no destructive capability, the severity is elevated to 'high' because it likely retrieves comprehensive personal information across Google Workspace services (emails, documents, calendar events, etc.), representing significant privacy exposure if misused by an untrusted agent.

From the tool's own definition: "Tool name contains 'read' and description states 'Read and retrieve the entire user' - clearly a retrieval operation with no modification capability."

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call memory_read_graph to retrieve information from VaultAssist without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches VaultAssist:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "memory_read_graph": {}
  }
}
```

## Other tools on VaultAssist (78)

- `batch_delete_gmail_emails` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/batch-delete-gmail-emails.md
- `clear_completed_tasks` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/clear-completed-tasks.md
- `delete_event` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/delete-event.md
- `delete_gmail_email` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/delete-gmail-email.md
- `delete_gmail_label` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/delete-gmail-label.md
- `delete_task` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/delete-task.md
- `delete_task_list` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/delete-task-list.md
- `memory_delete_entities` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/memory-delete-entities.md
- `memory_delete_observations` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/memory-delete-observations.md
- `memory_delete_relations` — Destructive — https://policylayer.com/tools/3xcaffeine-mcp-server/memory-delete-relations.md
- `roll_dice` — Other — https://policylayer.com/tools/3xcaffeine-mcp-server/roll-dice.md
- `sequentialthinking` — Other — https://policylayer.com/tools/3xcaffeine-mcp-server/sequentialthinking.md
- `about` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/about.md
- `debug_table_structure` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/debug-table-structure.md
- `echo` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/echo.md
- `get_doc_content` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-doc-content.md
- `get_drive_file_content` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-drive-file-content.md
- `get_event` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-event.md
- `get_events` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-events.md
- `get_form` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-form.md
- `get_form_response` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-form-response.md
- `get_page` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-page.md
- `get_page_thumbnail` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-page-thumbnail.md
- `get_presentation` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-presentation.md
- `get_spreadsheet_info` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-spreadsheet-info.md
- `get_task` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-task.md
- `get_task_list` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-task-list.md
- `get_user_info` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/get-user-info.md
- `inspect_doc_structure` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/inspect-doc-structure.md
- `list_calendars` — Read — https://policylayer.com/tools/3xcaffeine-mcp-server/list-calendars.md
- …and 48 more: https://policylayer.com/tools/3xcaffeine-mcp-server.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=3xcaffeine-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/3xcaffeine-mcp-server