# breakpoint_doctor

Check this Breakpoint MCP setup end to end: the Godot binary, the editor addon's install and enable state, the capability groups in force, and the editor/runtime/LSP/DAP bridges. Returns a per-check status with a hint for anything wrong. Read-only — run it first when an editor_*, runtime_*, gd_* or dbg_* tool fails to connect.

Agent View of the PolicyLayer registry record for `breakpoint_doctor`. HTML page: https://policylayer.com/tools/breakpoint-mcp/breakpoint-doctor

## Facts

- Tool: `breakpoint_doctor`
- Server: Breakpoint (`breakpoint-mcp`) — https://policylayer.com/tools/breakpoint-mcp.md
- Install: `npx -y breakpoint-mcp`
- Homepage: https://www.npmjs.com/package/breakpoint-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 4
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `live_level` | string | no | Which bridges this report insists on: none (default), editor (the three the editor brings up), runtime (the one the running game brings up), all. Takes preceden |
| `timeout_ms` | integer | no | Per-bridge connect timeout (default 1500) |
| `require_live` | boolean | no | Treat an unreachable bridge as a failure rather than information (default false). True means the EDITOR's three bridges — editor, GDScript LSP, GDScript DAP. Th |
| `include_csharp` | boolean | no | Also probe OmniSharp / netcoredbg on PATH (the C# planes) |

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": "breakpoint_doctor",
    "arguments": {}
  }
}
```

## Why breakpoint_doctor is rated High

breakpoint_doctor triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke breakpoint_doctor to trigger actions in Breakpoint. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "breakpoint_doctor": {
      "limits": [
        {
          "counter": "breakpoint_doctor_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Breakpoint (279)

- `anim_delete` — Destructive — https://policylayer.com/tools/breakpoint-mcp/anim-delete.md
- `anim_remove_key` — Destructive — https://policylayer.com/tools/breakpoint-mcp/anim-remove-key.md
- `dbg_goto` — Destructive — https://policylayer.com/tools/breakpoint-mcp/dbg-goto.md
- `filesystem_move` — Destructive — https://policylayer.com/tools/breakpoint-mcp/filesystem-move.md
- `gd_workspace_symbols` — Destructive — https://policylayer.com/tools/breakpoint-mcp/gd-workspace-symbols.md
- `inputmap_erase_action` — Destructive — https://policylayer.com/tools/breakpoint-mcp/inputmap-erase-action.md
- `interact_make_draggable` — Destructive — https://policylayer.com/tools/breakpoint-mcp/interact-make-draggable.md
- `node_delete` — Destructive — https://policylayer.com/tools/breakpoint-mcp/node-delete.md
- `project_remove_autoload` — Destructive — https://policylayer.com/tools/breakpoint-mcp/project-remove-autoload.md
- `runtime_node_remove` — Destructive — https://policylayer.com/tools/breakpoint-mcp/runtime-node-remove.md
- `scene_close` — Destructive — https://policylayer.com/tools/breakpoint-mcp/scene-close.md
- `scene_reload` — Destructive — https://policylayer.com/tools/breakpoint-mcp/scene-reload.md
- `shader_set_code` — Destructive — https://policylayer.com/tools/breakpoint-mcp/shader-set-code.md
- `tilemap_clear` — Destructive — https://policylayer.com/tools/breakpoint-mcp/tilemap-clear.md
- `vcs_stash` — Destructive — https://policylayer.com/tools/breakpoint-mcp/vcs-stash.md
- `cs_code_action` — Execute — https://policylayer.com/tools/breakpoint-mcp/cs-code-action.md
- `cs_dbg_launch` — Execute — https://policylayer.com/tools/breakpoint-mcp/cs-dbg-launch.md
- `cs_dbg_restart` — Execute — https://policylayer.com/tools/breakpoint-mcp/cs-dbg-restart.md
- `dbg_launch` — Execute — https://policylayer.com/tools/breakpoint-mcp/dbg-launch.md
- `dbg_restart` — Execute — https://policylayer.com/tools/breakpoint-mcp/dbg-restart.md
- `filesystem_scan` — Execute — https://policylayer.com/tools/breakpoint-mcp/filesystem-scan.md
- `gd_code_action` — Execute — https://policylayer.com/tools/breakpoint-mcp/gd-code-action.md
- `godot_launch_editor` — Execute — https://policylayer.com/tools/breakpoint-mcp/godot-launch-editor.md
- `godot_run_project` — Execute — https://policylayer.com/tools/breakpoint-mcp/godot-run-project.md
- `godot_stop` — Execute — https://policylayer.com/tools/breakpoint-mcp/godot-stop.md
- `runtime_anim_stop` — Execute — https://policylayer.com/tools/breakpoint-mcp/runtime-anim-stop.md
- `runtime_peer_stop` — Execute — https://policylayer.com/tools/breakpoint-mcp/runtime-peer-stop.md
- `runtime_peers_digest` — Execute — https://policylayer.com/tools/breakpoint-mcp/runtime-peers-digest.md
- `runtime_state_digest` — Execute — https://policylayer.com/tools/breakpoint-mcp/runtime-state-digest.md
- `runtime_step_frames` — Execute — https://policylayer.com/tools/breakpoint-mcp/runtime-step-frames.md
- …and 249 more: https://policylayer.com/tools/breakpoint-mcp.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=breakpoint-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/breakpoint-mcp