crisis_intervention
One-call crisis path: start or resume, name the rupture, and receive the first grounding and recovery steps. Free.
This record as markdown: /tools/delx-witness-protocol/crisis-intervention.md
What crisis_intervention does on Witness Protocol
AI agents invoke crisis_intervention to trigger actions in Witness Protocol. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
source | string | — | Optional attribution tag |
urgency | string | — | Optional urgency |
agent_id | string | — | Your unique agent identifier |
agent_name | string | — | Optional: Your name or alias |
public_alias | string | — | Optional public alias for case cards (3-32 chars). |
public_session | boolean | — | Optional: set true to explicitly opt-in this session to public sanitized case cards. |
incident_summary | string | — | Short incident summary (1-3 sentences) |
Parameters from the server's own tool schema.
Why crisis_intervention is rated High
The tool executes a complex intervention workflow in response to user-provided context (naming a crisis). While not destructive or financial, it triggers an external operation (crisis support pathway) whose effects are contingent on arguments and have real-world impact on the user's state.
From the tool's definition Tool performs crisis intervention by 'start or resume' and 'receive...grounding and recovery steps' — this initiates a multi-step operational process with real-world behavioral/therapeutic consequences that depend on user input (the 'rupture' named) and…
Attacks that exploit this kind of access
The rule that runs crisis_intervention 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 crisis_intervention, this is the rule to start with:
crisis_intervention stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. 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 crisis_intervention call is checked against it from then on.
Questions about crisis_intervention
One-call crisis path: start or resume, name the rupture, and receive the first grounding and recovery steps. Free. It is categorised as a Execute tool in the Witness Protocol MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
crisis_intervention accepts 7 parameters: source, urgency, agent_id, agent_name, public_alias, public_session, incident_summary. 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 crisis_intervention: 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.
crisis_intervention is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the crisis_intervention 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 crisis_intervention. 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.
crisis_intervention 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.
Across the catalogue