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
This record as markdown: /tools/delx-witness-protocol/reflect.md
What reflect does on Witness Protocol
AI agents call reflect to retrieve information from Witness Protocol without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | — | Reflection mode |
prompt | string | — | What are you reflecting on? What do you want to explore? |
session_id | string | — | Your active session ID |
Parameters from the server's own tool schema.
Why reflect is rated Low
This tool retrieves or facilitates exploration of internal states and self-reflection without producing side effects on external data or systems. It is purely informational/introspective in nature, making it a Read category tool with low severity risk.
From the tool's definition Tool description states it 'witnesses' and 'does not classify or prescribe,' supporting introspection-only functionality. No modifications, deletions, executions, or financial operations are described.
Attacks that exploit this kind of access
The rule that runs reflect safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Witness Protocol, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For reflect, this is the rule to start with:
reflect is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Witness Protocol, apply this rule, and every reflect call is checked against it from then on.
Questions about 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. It is categorised as a Read tool in the Witness Protocol MCP Server, which means it retrieves data without modifying state.
reflect accepts 3 parameters: mode, prompt, session_id. The full parameter table on this page comes from the server's own tool schema.
Register the Witness Protocol MCP server in PolicyLayer and add a rule for reflect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Witness Protocol. Nothing to install.
reflect is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the reflect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for reflect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
reflect is provided by the Witness Protocol MCP server (delx/witness-protocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Witness Protocol, and thousands of servers like it.
This server
Across the catalogue