Extract audit evidence requirements from a specific regulation section. Analyzes section text using 26 keyword patterns to identify required artifacts (policies, logs, risk assessments, training records, incident response plans, etc.). Distinguishes mandatory ("shall", "must") vs recommended ("sh...
Single-target operation
Part of the Us Regulations MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_evidence_requirements to retrieve information from Us Regulations 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_evidence_requirements 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.
tools:
get_evidence_requirements:
rules:
- action: allowSee the full Us Regulations policy for all 10 tools.
Extract audit evidence requirements from a specific regulation section. Analyzes section text using 26 keyword patterns to identify required artifacts (policies, logs, risk assessments, training records, incident response plans, etc.). Distinguishes mandatory ("shall", "must") vs recommended ("should", "may") evidence. Use this after identifying relevant sections via search_regulations or get_section. Output: { regulation, section, title, evidence: [{ type, description, mandatory, source_text }] }. Do not use this for discovery — use search_regulations first.. It is categorised as a Read tool in the Us Regulations MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_evidence_requirements. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Us Regulations MCP server.
get_evidence_requirements 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_evidence_requirements rule in your Intercept 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 Intercept policy for get_evidence_requirements. 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_evidence_requirements is provided by the Us Regulations MCP server (@ansvar/us-regulations-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept