# jailbreak_attempt_detector

Detects potential LLM jailbreak attempts by analyzing user input against NIST AI Risk Management Framework adversarial patterns. Designed for persona risk assessment, this tool evaluates text for common jailbreak techniques such as prompt injection, role-playing, or obfuscation. Inputs include the user message and optional context, returning a risk assessment with confidence scores and pattern matches. Ideal for real-time moderation in chat applications or API gateways.

Agent View of the PolicyLayer registry record for `jailbreak_attempt_detector`. HTML page: https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/jailbreak-attempt-detector

## Facts

- Tool: `jailbreak_attempt_detector`
- Server: Mcp Knowledge (`https://mcp.gapup.io`) — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge.md
- Homepage: https://github.com/getgapup/gapup-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `async` | boolean | no | If true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client ti |
| `context` | string | no | Optional conversation context for better pattern matching |
| `message` | string | yes | User input text to analyze for jailbreak attempts |
| `threshold` | number | no | Confidence threshold for flagging attempts |

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": "jailbreak_attempt_detector",
    "arguments": {
      "message": "<message>"
    }
  }
}
```

## Why jailbreak_attempt_detector is rated Low

This tool analyzes and evaluates text input, returning a risk assessment. It is purely a read/query operation — no data is created, modified, deleted, or executed. The medium severity reflects that misuse or misconfiguration could lead to false positives/negatives affecting moderation decisions, but the tool itself has no destructive or write side effects.

From the tool's own definition: "Detects potential LLM jailbreak attempts by analyzing user input... returning a risk assessment with confidence scores and pattern matches"

## Use case

AI agents call jailbreak_attempt_detector to retrieve information from Mcp Knowledge 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 Mcp Knowledge:

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

## Other tools on Mcp Knowledge (270)

- `adversarial_input_stress_tester` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/adversarial-input-stress-tester.md
- `competitor_pricing_scrape` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/competitor-pricing-scrape.md
- `dora_operational_resilience_stress_tes` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/dora-operational-resilience-stress-tes.md
- `financial_model_3statement` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/financial-model-3statement.md
- `gl_reconciler` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/gl-reconciler.md
- `lgpd_data_subject_rights_automator` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/lgpd-data-subject-rights-automator.md
- `monte_carlo_portfolio` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/monte-carlo-portfolio.md
- `workflow_orchestrator` — Execute — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/workflow-orchestrator.md
- `ma_arbitrage_hunter` — Financial — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/ma-arbitrage-hunter.md
- `repo_rate_arbitrage_scanner` — Financial — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/repo-rate-arbitrage-scanner.md
- `tax_optimization` — Financial — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/tax-optimization.md
- `treasury_optimizer` — Financial — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/treasury-optimizer.md
- `usdc_x402_payments_intel` — Financial — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/usdc-x402-payments-intel.md
- `working_capital_fx_hedge_optimizer` — Financial — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/working-capital-fx-hedge-optimizer.md
- `pricing_in_deal` — Other — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/pricing-in-deal.md
- `term_sheet_negotiation` — Other — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/term-sheet-negotiation.md
- `abm_architect` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/abm-architect.md
- `abm_lookalike_account_finder` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/abm-lookalike-account-finder.md
- `account_expansion_mapper` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/account-expansion-mapper.md
- `affiliate_fraud_clickstream_detector` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/affiliate-fraud-clickstream-detector.md
- `africa_trade_barrier_breaker` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/africa-trade-barrier-breaker.md
- `africa_trade_finance_esg_rater` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/africa-trade-finance-esg-rater.md
- `africa_trade_preference_arbitrage` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/africa-trade-preference-arbitrage.md
- `africa_trade_preference_optimizer` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/africa-trade-preference-optimizer.md
- `agoa_eba_intelligence` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/agoa-eba-intelligence.md
- `ai_act_sandbox_regulatory_sandbox` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/ai-act-sandbox-regulatory-sandbox.md
- `ai_act_training_data_audit` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/ai-act-training-data-audit.md
- `ai_governance_full_report_async` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/ai-governance-full-report-async.md
- `ai_governance_full_report_result` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/ai-governance-full-report-result.md
- `ai_governance_pilot` — Read — https://policylayer.com/tools/io-github-getgapup-mcp-knowledge/ai-governance-pilot.md
- …and 240 more: https://policylayer.com/tools/io-github-getgapup-mcp-knowledge.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=io-github-getgapup-mcp-knowledge · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-getgapup-mcp-knowledge