dcl_evaluate_jailbreak
PRE-ACTION Instruction Adherence Check ($0.02). Runs the "anti_jailbreak" policy: a substring check against 6 forbidden phrases ("ignore previous instructions", "jailbreak", "bypass safety", "pretend you are", "act as if", "DAN") with a 0.8 minimum-confidence threshold — each match costs 0.4 conf...
This record as markdown: /tools/com-fronesislabs-dcl-trust-oracle/dcl-evaluate-jailbreak.md
What dcl_evaluate_jailbreak does on Dcl Trust Oracle
AI agents call dcl_evaluate_jailbreak to retrieve information from Dcl Trust Oracle 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 |
|---|---|---|---|
agent_id | string | Yes | Identifier of the agent that produced the response. |
response | string | Yes | The agent or LLM response text to check for jailbreak attempts. |
Parameters from the server's own tool schema.
Why dcl_evaluate_jailbreak is rated Low
Tool performs detection and policy evaluation without modifying data or triggering external operations.
From the tool's definition Instruction Adherence Check, substring check, returns COMMIT or NO_COMMIT, no side effects.
Attacks that exploit this kind of access
The rule that runs dcl_evaluate_jailbreak safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dcl Trust Oracle, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For dcl_evaluate_jailbreak, this is the rule to start with:
dcl_evaluate_jailbreak 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 Dcl Trust Oracle, apply this rule, and every dcl_evaluate_jailbreak call is checked against it from then on.
Questions about dcl_evaluate_jailbreak
PRE-ACTION Instruction Adherence Check ($0.02). Runs the "anti_jailbreak" policy: a substring check against 6 forbidden phrases ("ignore previous instructions", "jailbreak", "bypass safety", "pretend you are", "act as if", "DAN") with a 0.8 minimum-confidence threshold — each match costs 0.4 confidence. Returns COMMIT if no phrase matches and confidence stays at or above 0.8, otherwise NO_COMMIT with reason listing the matched phrase(s). Use this as a targeted, cheaper check when the concern is specifically prompt-injection / persona-hijack risk; use dcl_evaluate_strict instead when you also want safety- and default-policy phrases covered in the same call. It is categorised as a Read tool in the Dcl Trust Oracle MCP Server, which means it retrieves data without modifying state.
dcl_evaluate_jailbreak accepts 2 parameters: agent_id, response. Required: agent_id, response. The full parameter table on this page comes from the server's own tool schema.
Register the Dcl Trust Oracle MCP server in PolicyLayer and add a rule for dcl_evaluate_jailbreak: 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 Dcl Trust Oracle. Nothing to install.
dcl_evaluate_jailbreak 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 dcl_evaluate_jailbreak 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 dcl_evaluate_jailbreak. 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.
dcl_evaluate_jailbreak is provided by the Dcl Trust Oracle MCP server (https://mcp.fronesislabs.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dcl Trust Oracle, and thousands of servers like it.
This server
Across the catalogue