# get_session_focus

Read the referee-authored current scene, phase, and location. The narrating AI receives the public scene summary but not private DM notes and cannot change the scene through this tool.

Agent View of the PolicyLayer registry record for `get_session_focus`. HTML page: https://policylayer.com/tools/torch-to-crown/get-session-focus

## Facts

- Tool: `get_session_focus`
- Server: Torch-to-Crown (`Diogenes187/Torch-to-Crown`) — https://policylayer.com/tools/torch-to-crown.md
- Homepage: https://github.com/Diogenes187/Torch-to-Crown
- 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": "get_session_focus",
    "arguments": {}
  }
}
```

## Why get_session_focus is rated Low

Even though get_session_focus 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 get_session_focus to retrieve information from Torch-to-Crown 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 Torch-to-Crown:

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

## Other tools on Torch-to-Crown (450)

- `cast_atonement` — Destructive — https://policylayer.com/tools/torch-to-crown/cast-atonement.md
- `cast_force_motion_magic` — Destructive — https://policylayer.com/tools/torch-to-crown/cast-force-motion-magic.md
- `cast_legend_lore` — Destructive — https://policylayer.com/tools/torch-to-crown/cast-legend-lore.md
- `cast_object_magic` — Destructive — https://policylayer.com/tools/torch-to-crown/cast-object-magic.md
- `cast_residual_transformation_magic` — Destructive — https://policylayer.com/tools/torch-to-crown/cast-residual-transformation-magic.md
- `cast_shape_change` — Destructive — https://policylayer.com/tools/torch-to-crown/cast-shape-change.md
- `change_character_possession` — Destructive — https://policylayer.com/tools/torch-to-crown/change-character-possession.md
- `destroy_plant_door_tree` — Destructive — https://policylayer.com/tools/torch-to-crown/destroy-plant-door-tree.md
- `destroy_snake_stick` — Destructive — https://policylayer.com/tools/torch-to-crown/destroy-snake-stick.md
- `disarm_trap` — Destructive — https://policylayer.com/tools/torch-to-crown/disarm-trap.md
- `force_door` — Destructive — https://policylayer.com/tools/torch-to-crown/force-door.md
- `force_scared_creature_to_fight` — Destructive — https://policylayer.com/tools/torch-to-crown/force-scared-creature-to-fight.md
- `record_familiar_death` — Destructive — https://policylayer.com/tools/torch-to-crown/record-familiar-death.md
- `remove_combatant` — Destructive — https://policylayer.com/tools/torch-to-crown/remove-combatant.md
- `remove_deafness_by_caster` — Destructive — https://policylayer.com/tools/torch-to-crown/remove-deafness-by-caster.md
- `remove_spell_trap` — Destructive — https://policylayer.com/tools/torch-to-crown/remove-spell-trap.md
- `resolve_animate_dead` — Destructive — https://policylayer.com/tools/torch-to-crown/resolve-animate-dead.md
- `stand_up` — Destructive — https://policylayer.com/tools/torch-to-crown/stand-up.md
- `trigger_spell_trap` — Destructive — https://policylayer.com/tools/torch-to-crown/trigger-spell-trap.md
- `use_prismatic_barrier` — Destructive — https://policylayer.com/tools/torch-to-crown/use-prismatic-barrier.md
- `use_read_magic` — Destructive — https://policylayer.com/tools/torch-to-crown/use-read-magic.md
- `cast_manifestation_illusion` — Execute — https://policylayer.com/tools/torch-to-crown/cast-manifestation-illusion.md
- `cast_spell_trap` — Execute — https://policylayer.com/tools/torch-to-crown/cast-spell-trap.md
- `cast_time_stop` — Execute — https://policylayer.com/tools/torch-to-crown/cast-time-stop.md
- `deploy_aerial_servant` — Execute — https://policylayer.com/tools/torch-to-crown/deploy-aerial-servant.md
- `start_combat` — Execute — https://policylayer.com/tools/torch-to-crown/start-combat.md
- `start_wandering_combat` — Execute — https://policylayer.com/tools/torch-to-crown/start-wandering-combat.md
- `trigger_arcane_symbol` — Execute — https://policylayer.com/tools/torch-to-crown/trigger-arcane-symbol.md
- `trigger_cleric_symbol` — Execute — https://policylayer.com/tools/torch-to-crown/trigger-cleric-symbol.md
- `trigger_drain_glyph` — Execute — https://policylayer.com/tools/torch-to-crown/trigger-drain-glyph.md
- …and 420 more: https://policylayer.com/tools/torch-to-crown.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=torch-to-crown · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/torch-to-crown