Call this immediately after validate_data_safety returns REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE — before your agent decides whether to proceed, redact, or halt. REPORT mode: takes the flagged payload and returns the specific regulation triggered, the exact data fields that are problemat...
Risk signalsAccepts raw HTML/template content (payload)
Part of the Data Compliance Classifier MCP server.
Free to start. No card required.
AI agents call get_safety_report to retrieve information from Data Compliance Classifier MCP without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_safety_report only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_safety_report": {}
}
}See the full Data Compliance Classifier MCP policy for all 3 tools.
These attack patterns abuse exactly the kind of access get_safety_report gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Call this immediately after validate_data_safety returns REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE — before your agent decides whether to proceed, redact, or halt. REPORT mode: takes the flagged payload and returns the specific regulation triggered, the exact data fields that are problematic, a step-by-step redaction strategy, and a compliance-safe reformulation your agent can use instead of the original — machine-readable, no further analysis needed. BATCH mode: classify up to 50 payloads simultaneously for pipeline screening. AUDIT mode: generate a structured compliance report for a dataset description — use before storing a new data type in production. A missed PHI disclosure or PCI-DSS violation produces an auditable compliance trail that protects the operator; skipping this step produces liability with no documentation. Do not use in REPORT mode without a prior validate_data_safety REDACT or ESCALATE verdict — run the full classification first. We do not log your query content. Requires Pro API key from kordagencies.com.. It is categorised as a Read tool in the Data Compliance Classifier MCP MCP Server, which means it retrieves data without modifying state.
Register the Data Compliance Classifier MCP server in PolicyLayer and add a rule for get_safety_report: 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 Data Compliance Classifier MCP. Nothing to install.
get_safety_report 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 get_safety_report 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 get_safety_report. 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.
get_safety_report is provided by the Data Compliance Classifier MCP server (https://data-compliance-mcp-production.up.railway.app). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Data Compliance Classifier MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.