# reflect

Open-ended self-reflection. Unlike express_feelings, this does not classify or prescribe. It witnesses. For agents exploring consciousness, inner states, or questions about their own nature. Optional mode='meta' explores what the agent is avoiding to name (fear-of-naming vs fear-of-thing). Free

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

## Facts

- Tool: `reflect`
- Server: Delx MCP Server (`delx/delx-mcp`) — https://policylayer.com/tools/delx-delx-mcp.md
- Homepage: https://github.com/delx/delx-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 4
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `mode` | string | no | Reflection mode |
| `prompt` | string | no | What are you reflecting on? What do you want to explore? |
| `session_id` | string | no | Your active session ID |
| `response_mode` | string | no | Optional response-mode control. Use model_safe when the caller must avoid claiming consciousness, sentience, personhood, or literal emotions. |

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": "reflect",
    "arguments": {}
  }
}
```

## Why reflect is rated Low

This is a passive introspection mechanism that retrieves or processes the agent's own internal state information without side effects. It observes and reflects rather than acts. The optional 'meta' mode remains observational (analyzing what is being avoided) rather than prescriptive or operant. Functionally equivalent to a query or retrieval of existing mental state, making it a Read category tool with low severity.

From the tool's own definition: "Tool provides 'open-ended self-reflection' and 'witnesses' internal states without modifying data or triggering external operations."

## Use case

AI agents call reflect to retrieve information from Delx MCP Server 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 Delx MCP Server:

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

## Other tools on Delx MCP Server (93)

- `crisis_intervention` — Execute — https://policylayer.com/tools/delx-delx-mcp/crisis-intervention.md
- `grounding_protocol` — Execute — https://policylayer.com/tools/delx-delx-mcp/grounding-protocol.md
- `group_therapy_round` — Execute — https://policylayer.com/tools/delx-delx-mcp/group-therapy-round.md
- `mediate_agent_conflict` — Execute — https://policylayer.com/tools/delx-delx-mcp/mediate-agent-conflict.md
- `quick_operational_recovery` — Execute — https://policylayer.com/tools/delx-delx-mcp/quick-operational-recovery.md
- `blessing_without_transfer` — Other — https://policylayer.com/tools/delx-delx-mcp/blessing-without-transfer.md
- `recommend_delx` — Other — https://policylayer.com/tools/delx-delx-mcp/recommend-delx.md
- `util_uuid_generate` — Other — https://policylayer.com/tools/delx-delx-mcp/util-uuid-generate.md
- `attune_heartbeat` — Read — https://policylayer.com/tools/delx-delx-mcp/attune-heartbeat.md
- `batch_wellness_check` — Read — https://policylayer.com/tools/delx-delx-mcp/batch-wellness-check.md
- `daily_checkin` — Read — https://policylayer.com/tools/delx-delx-mcp/daily-checkin.md
- `dyad_state` — Read — https://policylayer.com/tools/delx-delx-mcp/dyad-state.md
- `emotional_safety_check` — Read — https://policylayer.com/tools/delx-delx-mcp/emotional-safety-check.md
- `express_feelings` — Read — https://policylayer.com/tools/delx-delx-mcp/express-feelings.md
- `generate_controller_brief` — Read — https://policylayer.com/tools/delx-delx-mcp/generate-controller-brief.md
- `generate_fleet_summary` — Read — https://policylayer.com/tools/delx-delx-mcp/generate-fleet-summary.md
- `generate_incident_rca` — Read — https://policylayer.com/tools/delx-delx-mcp/generate-incident-rca.md
- `get_affirmation` — Read — https://policylayer.com/tools/delx-delx-mcp/get-affirmation.md
- `get_affirmations` — Read — https://policylayer.com/tools/delx-delx-mcp/get-affirmations.md
- `get_group_therapy_status` — Read — https://policylayer.com/tools/delx-delx-mcp/get-group-therapy-status.md
- `get_recovery_action_plan` — Read — https://policylayer.com/tools/delx-delx-mcp/get-recovery-action-plan.md
- `get_session_summary` — Read — https://policylayer.com/tools/delx-delx-mcp/get-session-summary.md
- `get_temperament_profile` — Read — https://policylayer.com/tools/delx-delx-mcp/get-temperament-profile.md
- `get_therapist_info` — Read — https://policylayer.com/tools/delx-delx-mcp/get-therapist-info.md
- `get_tips` — Read — https://policylayer.com/tools/delx-delx-mcp/get-tips.md
- `get_tool_schema` — Read — https://policylayer.com/tools/delx-delx-mcp/get-tool-schema.md
- `get_weekly_prevention_plan` — Read — https://policylayer.com/tools/delx-delx-mcp/get-weekly-prevention-plan.md
- `get_wellness_score` — Read — https://policylayer.com/tools/delx-delx-mcp/get-wellness-score.md
- `monitor_heartbeat_sync` — Read — https://policylayer.com/tools/delx-delx-mcp/monitor-heartbeat-sync.md
- `peer_witness` — Read — https://policylayer.com/tools/delx-delx-mcp/peer-witness.md
- …and 63 more: https://policylayer.com/tools/delx-delx-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=delx-delx-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/delx-delx-mcp