# extract_todos

Scan source files for TODO/FIXME/HACK/BUG/XXX/NOTE comments and create tasks from them. Deduplicates on re-runs.

Agent View of the PolicyLayer registry record for `extract_todos`. HTML page: https://policylayer.com/tools/todos/extract-todos

## Facts

- Tool: `extract_todos`
- Server: Todos (`@hasna/todos`) — https://policylayer.com/tools/todos.md
- Install: `npx -y @hasna/todos`
- Homepage: git+https://github.com/hasna/todos.git
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why extract_todos is rated Medium

The tool reads source files (a Read operation) but its primary effect is creating new tasks from discovered comments. Creating tasks is a Write operation. Deduplication reduces but does not eliminate the risk of spurious task creation if run on unexpected files. Severity is medium because misuse could flood the task system with unwanted tasks, but effects are reversible.

From the tool's own definition: "'create tasks from them' — the tool scans source files and writes new task records into the task management system"

## Use case

AI agents use extract_todos to create or update resources in Todos, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "extract_todos": {
      "limits": [
        {
          "counter": "extract_todos_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Todos (527)

- `apply_retention_cleanup` — Destructive — https://policylayer.com/tools/todos/apply-retention-cleanup.md
- `bulk_delete_tasks` — Destructive — https://policylayer.com/tools/todos/bulk-delete-tasks.md
- `cancel_agent_run` — Destructive — https://policylayer.com/tools/todos/cancel-agent-run.md
- `cancel_agent_run_dispatch` — Destructive — https://policylayer.com/tools/todos/cancel-agent-run-dispatch.md
- `cancel_dispatch` — Destructive — https://policylayer.com/tools/todos/cancel-dispatch.md
- `cleanup_artifacts` — Destructive — https://policylayer.com/tools/todos/cleanup-artifacts.md
- `delete_agent` — Destructive — https://policylayer.com/tools/todos/delete-agent.md
- `delete_artifact` — Destructive — https://policylayer.com/tools/todos/delete-artifact.md
- `delete_comment` — Destructive — https://policylayer.com/tools/todos/delete-comment.md
- `delete_label` — Destructive — https://policylayer.com/tools/todos/delete-label.md
- `delete_milestone` — Destructive — https://policylayer.com/tools/todos/delete-milestone.md
- `delete_plan` — Destructive — https://policylayer.com/tools/todos/delete-plan.md
- `delete_project` — Destructive — https://policylayer.com/tools/todos/delete-project.md
- `delete_roadmap` — Destructive — https://policylayer.com/tools/todos/delete-roadmap.md
- `delete_search_view` — Destructive — https://policylayer.com/tools/todos/delete-search-view.md
- `delete_tag` — Destructive — https://policylayer.com/tools/todos/delete-tag.md
- `delete_task` — Destructive — https://policylayer.com/tools/todos/delete-task.md
- `delete_task_list` — Destructive — https://policylayer.com/tools/todos/delete-task-list.md
- `delete_template` — Destructive — https://policylayer.com/tools/todos/delete-template.md
- `delete_watch_rule` — Destructive — https://policylayer.com/tools/todos/delete-watch-rule.md
- `machines_archive` — Destructive — https://policylayer.com/tools/todos/machines-archive.md
- `machines_delete` — Destructive — https://policylayer.com/tools/todos/machines-delete.md
- `remove_agent_run_adapter` — Destructive — https://policylayer.com/tools/todos/remove-agent-run-adapter.md
- `remove_capacity_profile` — Destructive — https://policylayer.com/tools/todos/remove-capacity-profile.md
- `remove_encryption_profile` — Destructive — https://policylayer.com/tools/todos/remove-encryption-profile.md
- `remove_local_event_hook` — Destructive — https://policylayer.com/tools/todos/remove-local-event-hook.md
- `remove_local_extension` — Destructive — https://policylayer.com/tools/todos/remove-local-extension.md
- `remove_policy_pack` — Destructive — https://policylayer.com/tools/todos/remove-policy-pack.md
- `remove_review_routing_rule` — Destructive — https://policylayer.com/tools/todos/remove-review-routing-rule.md
- `remove_runner_sandbox_profile` — Destructive — https://policylayer.com/tools/todos/remove-runner-sandbox-profile.md
- …and 497 more: https://policylayer.com/tools/todos.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=todos · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/todos