# drive_read_file

Read a file from a drive. Text comes back as utf-8 content; binary as contentBase64. Files over 1 MB are refused (use the skill scripts).

Agent View of the PolicyLayer registry record for `drive_read_file`. HTML page: https://policylayer.com/tools/ai-dataecho-mcp/drive-read-file

## Facts

- Tool: `drive_read_file`
- Server: Mcp (`https://dataecho.ai/mcp`) — https://policylayer.com/tools/ai-dataecho-mcp.md
- Homepage: https://github.com/mohocp/dataecho
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 2 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | yes | File path in the drive |
| `drive` | string | yes | Drive name or drv_… id |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "drive_read_file",
    "arguments": {
      "path": "<path>",
      "drive": "<drive>"
    }
  }
}
```

## Why drive_read_file is rated Low

This tool retrieves file contents from a drive with no side effects, no data modification, and no destructive capability. It is a straightforward read operation. The 1 MB file size limit is a safety constraint, not indicative of higher risk. Severity is low because unauthorized file reads depend on what secrets/data exist in the drive, but the tool itself has minimal blast radius without additional context.

From the tool's own definition: "Tool name is 'drive_read_file' and description explicitly states 'Read a file from a drive.' Returns file content without modification or deletion. Binary files returned as base64, text as utf-8."

Risk signals: Accepts file system path (path)

## Use case

AI agents call drive_read_file to retrieve information from Mcp 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 Mcp:

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

## Other tools on Mcp (25)

- `delete_site` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/delete-site.md
- `delete_variable` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/delete-variable.md
- `drive_delete_file` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/drive-delete-file.md
- `drive_revoke_token` — Destructive — https://policylayer.com/tools/ai-dataecho-mcp/drive-revoke-token.md
- `app_status` — Read — https://policylayer.com/tools/ai-dataecho-mcp/app-status.md
- `drive_history` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-history.md
- `drive_list_files` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-list-files.md
- `drive_tokens` — Read — https://policylayer.com/tools/ai-dataecho-mcp/drive-tokens.md
- `get_site` — Read — https://policylayer.com/tools/ai-dataecho-mcp/get-site.md
- `list_drives` — Read — https://policylayer.com/tools/ai-dataecho-mcp/list-drives.md
- `list_sites` — Read — https://policylayer.com/tools/ai-dataecho-mcp/list-sites.md
- `list_variables` — Read — https://policylayer.com/tools/ai-dataecho-mcp/list-variables.md
- `platform_info` — Read — https://policylayer.com/tools/ai-dataecho-mcp/platform-info.md
- `search_sites` — Read — https://policylayer.com/tools/ai-dataecho-mcp/search-sites.md
- `verify_login_code` — Read — https://policylayer.com/tools/ai-dataecho-mcp/verify-login-code.md
- `claim_site` — Write — https://policylayer.com/tools/ai-dataecho-mcp/claim-site.md
- `create_drive` — Write — https://policylayer.com/tools/ai-dataecho-mcp/create-drive.md
- `drive_move_file` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-move-file.md
- `drive_restore` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-restore.md
- `drive_share` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-share.md
- `drive_write_file` — Write — https://policylayer.com/tools/ai-dataecho-mcp/drive-write-file.md
- `publish_site` — Write — https://policylayer.com/tools/ai-dataecho-mcp/publish-site.md
- `request_login_code` — Write — https://policylayer.com/tools/ai-dataecho-mcp/request-login-code.md
- `set_variable` — Write — https://policylayer.com/tools/ai-dataecho-mcp/set-variable.md
- `update_site_metadata` — Write — https://policylayer.com/tools/ai-dataecho-mcp/update-site-metadata.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=ai-dataecho-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/ai-dataecho-mcp