# extract_text

A read tool on the Aos MCP server.

Agent View of the PolicyLayer registry record for `extract_text`. HTML page: https://policylayer.com/tools/hybridlabor-api-aos/extract-text

## Facts

- Tool: `extract_text`
- Server: Aos (`@hybridlabor-api/aos`) — https://policylayer.com/tools/hybridlabor-api-aos.md
- Install: `npx -y @hybridlabor-api/aos`
- Homepage: git+https://github.com/hybridlabor-api/aos.git
- 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": "extract_text",
    "arguments": {}
  }
}
```

## Why extract_text is rated Low

The name 'extract_text' suggests reading and retrieving text content from a source without modification or deletion. This falls under the Read category as it queries or retrieves data. Confidence is moderate rather than high due to the empty description, but the name provides reasonably clear intent.

From the tool's own definition: "Tool name 'extract_text' indicates data retrieval/extraction with no side effects. The tool description is empty, limiting direct evidence."

## Use case

AI agents call extract_text to retrieve information from Aos 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 Aos:

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

## Other tools on Aos (718)

- `archive_project` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/archive-project.md
- `clear_clip_flags` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/clear-clip-flags.md
- `clear_layer` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/clear-layer.md
- `close_window` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/close-window.md
- `delete_clip_markers` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-clip-markers.md
- `delete_color_group` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-color-group.md
- `delete_color_version` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-color-version.md
- `delete_face` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-face.md
- `delete_fusion_comp_on_clip` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-fusion-comp-on-clip.md
- `delete_layer` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-layer.md
- `delete_markers` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-markers.md
- `delete_media_pool_clips` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-media-pool-clips.md
- `delete_objects` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-objects.md
- `delete_project` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-project.md
- `delete_render_job` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-render-job.md
- `delete_stills` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-stills.md
- `delete_take` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-take.md
- `delete_td_node` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-td-node.md
- `delete_timeline_clips` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-timeline-clips.md
- `delete_track` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/delete-track.md
- `manage_checkpoint` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/manage-checkpoint.md
- `remoteos_manage_instance` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/remoteos-manage-instance.md
- `remove_background_clip` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/remove-background-clip.md
- `repair_network` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/repair-network.md
- `reset_all_grades` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/reset-all-grades.md
- `unlink_media_pool_clips` — Destructive — https://policylayer.com/tools/hybridlabor-api-aos/unlink-media-pool-clips.md
- `add_render_job` — Execute — https://policylayer.com/tools/hybridlabor-api-aos/add-render-job.md
- `ae_render_active_comp` — Execute — https://policylayer.com/tools/hybridlabor-api-aos/ae-render-active-comp.md
- `apply_glsl_top_mapping` — Execute — https://policylayer.com/tools/hybridlabor-api-aos/apply-glsl-top-mapping.md
- `apply_transform` — Execute — https://policylayer.com/tools/hybridlabor-api-aos/apply-transform.md
- …and 688 more: https://policylayer.com/tools/hybridlabor-api-aos.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=hybridlabor-api-aos · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/hybridlabor-api-aos