Retrieve test cases for your agent. If generation_id is provided, checks that specific generation's status and returns results when ready. Otherwise returns the latest available test cases. WHEN TO USE: Phase 2, Step 8-9 — to check generation status or retrieve generated test cases. AFTER THIS:...
Part of the Invarium MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call invarium_get_tests to retrieve information from Invarium 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 invarium_get_tests 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:
invarium_get_tests:
rules:
- action: allowSee the full Invarium policy for all 19 tools.
Agents calling read-class tools like invarium_get_tests have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Retrieve test cases for your agent. If generation_id is provided, checks that specific generation's status and returns results when ready. Otherwise returns the latest available test cases. WHEN TO USE: Phase 2, Step 8-9 — to check generation status or retrieve generated test cases. AFTER THIS: Present the test cases to the user. Do NOT automatically chain into another tool call. Ask: "These are the generated test cases. Ready to run them against your agent, or want to review/modify first?" If generation is still in progress, wait 5-10 seconds and ask the user if they want to check again or work on something else. Args: agent_name: Name of the agent to retrieve tests for. generation_id: Optional generation ID from invarium_generate_tests. output_format: Output format — "text" (default) for readable output, "json" for raw JSON. output_file: Optional file path to save test cases as JSON. offset: Number of test cases to skip for pagination (default: 0). limit: Maximum test cases to return per page (default: 20).. It is categorised as a Read tool in the Invarium MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for invarium_get_tests. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Invarium MCP server.
invarium_get_tests 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 invarium_get_tests 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 invarium_get_tests. 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.
invarium_get_tests is provided by the Invarium MCP server (invarium-ai/invarium). 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