# binary_read

Read bounded bytes from disk by zero-based byte offset; never read an editor buffer.

Agent View of the PolicyLayer registry record for `binary_read`. HTML page: https://policylayer.com/tools/010-editor-mcp/binary-read

## Facts

- Tool: `binary_read`
- Server: 010 Editor (`AuroraAeon/010-editor-mcp`) — https://policylayer.com/tools/010-editor-mcp.md
- Homepage: https://github.com/AuroraAeon/010-editor-mcp
- Risk category: Read (Low risk)
- Registry record: grade D, 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": "binary_read",
    "arguments": {}
  }
}
```

## Why binary_read is rated Low

Even though binary_read only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call binary_read to retrieve information from 010 Editor 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 010 Editor:

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

## Other tools on 010 Editor (13)

- `editor_run_template` — Execute — https://policylayer.com/tools/010-editor-mcp/editor-run-template.md
- `binary_diff` — Read — https://policylayer.com/tools/010-editor-mcp/binary-diff.md
- `binary_inspect` — Read — https://policylayer.com/tools/010-editor-mcp/binary-inspect.md
- `binary_search` — Read — https://policylayer.com/tools/010-editor-mcp/binary-search.md
- `editor_context` — Read — https://policylayer.com/tools/010-editor-mcp/editor-context.md
- `editor_read` — Read — https://policylayer.com/tools/010-editor-mcp/editor-read.md
- `editor_status` — Read — https://policylayer.com/tools/010-editor-mcp/editor-status.md
- `server_status` — Read — https://policylayer.com/tools/010-editor-mcp/server-status.md
- `binary_patch_apply` — Write — https://policylayer.com/tools/010-editor-mcp/binary-patch-apply.md
- `binary_patch_preview` — Write — https://policylayer.com/tools/010-editor-mcp/binary-patch-preview.md
- `editor_patch_apply` — Write — https://policylayer.com/tools/010-editor-mcp/editor-patch-apply.md
- `editor_patch_preview` — Write — https://policylayer.com/tools/010-editor-mcp/editor-patch-preview.md
- `editor_select` — Write — https://policylayer.com/tools/010-editor-mcp/editor-select.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=010-editor-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/010-editor-mcp