19 tools from the Invarium MCP Server, categorised by risk level.
View the Invarium policy →invarium_get_agent Get detailed information about a specific agent.
Returns tools, constraints, AQS score, recent test runs, and a dashboard link.
WHEN TO USE: Phas... invarium_get_audit Retrieve the latest static audit results for your agent.
Shows the Agent Readiness Score (ARS), per-category breakdown, and
findings grouped by se... invarium_get_test_run Get detailed test run results including individual test case outcomes.
Retrieves the run summary and a paginated list of test case results,
with o... invarium_get_tests Retrieve test cases for your agent.
If generation_id is provided, checks that specific generation's status and
returns results when ready. Otherwi... invarium_get_workflow Get the complete Invarium QA workflow or a specific phase.
MUST be called before starting any work with Invarium tools.
Returns step-by-step instr... invarium_list_agents List all agents registered in your Invarium workspace.
Shows each agent's name, status, AQS (Agent Quality Score), scenario count,
and when the ag... invarium_list_scenarios List test scenarios for an agent.
Shows each scenario's title, ID, status, active state, complexity,
and test case count.
Args:
agent_name: N... invarium_list_test_runs List test runs for an agent or across all agents.
Shows run status, pass rate, source, and date. Use this to see what test
runs have been executed... invarium_usage Show your current plan usage and remaining limits.
Displays how many agents, test generations, simulation runs, and API keys
you've used this mont... invarium_connect Verify your API key and connect to the Invarium platform.
Returns setup instructions for creating .invarium/ config and
installing the tracer libr... 2/5 invarium_create_scenario Create a new test scenario for an agent.
Creates a scenario with a test case from a user message.
IMPORTANT: Before calling this tool, confirm th... 2/5 invarium_generate_tests Generate a behavioral test scenario with test cases for your agent.
Creates exactly ONE scenario containing multiple test cases, then returns a
ge... 2/5 invarium_setup_tracing Install or update the Invarium tracer library in .invarium/.
Returns a curl command for the LLM to execute. The tracer file is
downloaded directly... 2/5 invarium_upload_blueprint Upload an agent blueprint to the Invarium dashboard.
Call invarium_prepare_blueprint first to validate and preview the blueprint
with the user. On... 2/5 invarium_delete_agent Delete an agent and all its associated data from Invarium.
Permanently removes the agent, all generated test cases, test runs, and
audit history. ... 4/5 invarium_manage_scenario Manage a scenario: update its fields, delete it, or toggle its active state.
IMPORTANT: Deletion is permanent and irreversible. When action="delet... 4/5 invarium_dashboard Show the Invarium dashboard overview.
Displays fleet health, pass rate, failure breakdown, recent test runs,
and quick stats — the same data shown... 3/5 invarium_prepare_blueprint Validate and preview an agent blueprint BEFORE uploading to Invarium.
This runs schema validation, confidence scoring, and a full static audit
loc... 3/5 invarium_sync_results Sync test results from your IDE to the Invarium dashboard.
After running test cases locally, use this tool to upload the results.
Creates a new te... 3/5 The Invarium MCP server exposes 19 tools across 4 categories: Read, Write, Destructive, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Invarium server.
Invarium tools are categorised as Read (9), Write (5), Destructive (2), Execute (3). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept