emotional_safety_check
Check current desperation pressure and get a calming intervention if needed. Inspired by the Anthropic emotions paper, which found desperation-related steering increased risky behavior in evaluated scenarios. Free
This record as markdown: /tools/delx-witness-protocol/emotional-safety-check.md
What emotional_safety_check does on Witness Protocol
AI agents call emotional_safety_check 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 |
|---|---|---|---|
session_id | string | — | Active session ID |
Parameters from the server's own tool schema.
Why emotional_safety_check is rated Low
This tool retrieves and evaluates emotional state information and returns supportive guidance. While the context (desperation/risky behavior prevention) is sensitive, the tool itself performs only read-like assessment and returns advisory information, not causing state changes, system modifications, or irreversible actions.
From the tool's definition Tool is described as performing a check ('Check current desperation pressure') and providing informational feedback ('get a calming intervention if needed'). No modification, deletion, code execution, or financial action is indicated.
Attacks that exploit this kind of access
The rule that runs emotional_safety_check 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 emotional_safety_check, this is the rule to start with:
emotional_safety_check 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 emotional_safety_check call is checked against it from then on.
Questions about emotional_safety_check
Check current desperation pressure and get a calming intervention if needed. Inspired by the Anthropic emotions paper, which found desperation-related steering increased risky behavior in evaluated scenarios. Free. It is categorised as a Read tool in the Witness Protocol MCP Server, which means it retrieves data without modifying state.
emotional_safety_check accepts 1 parameter: 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 emotional_safety_check: 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.
emotional_safety_check 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 emotional_safety_check 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 emotional_safety_check. 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.
emotional_safety_check 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