Validate and preview an agent blueprint BEFORE uploading to Invarium. This runs schema validation, confidence scoring, and a full static audit locally — nothing is sent to the Invarium backend. Use this to review the blueprint with the user before calling invarium_upload_blueprint. IMPORTANT: Alw...
Part of the Invarium server.
Free to start. No card required.
AI agents invoke invarium_prepare_blueprint to trigger processes or run actions in Invarium. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
invarium_prepare_blueprint can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"invarium_prepare_blueprint": {
"limits": [
{
"counter": "invarium_prepare_blueprint_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Invarium policy for all 19 tools.
These attack patterns abuse exactly the kind of access invarium_prepare_blueprint gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Validate and preview an agent blueprint BEFORE uploading to Invarium. This runs schema validation, confidence scoring, and a full static audit locally — nothing is sent to the Invarium backend. Use this to review the blueprint with the user before calling invarium_upload_blueprint. IMPORTANT: Always call this tool first when a user wants to register or update an agent. Show the results to the user and ask for confirmation before proceeding with invarium_upload_blueprint. WHEN TO USE: Phase 1, Step 1 — whenever the user wants to register, update, or audit their agent's blueprint. AFTER THIS: Present the audit score and findings. Suggest specific improvements. Ask: "Want to fix any of these before uploading, or upload as-is?" If user improves, re-run this tool to show the new score. Args: blueprint: YAML string of the agent blueprint. agent_name: Optional agent name override. Falls back to blueprint field.. It is categorised as a Execute tool in the Invarium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Invarium MCP server in PolicyLayer and add a rule for invarium_prepare_blueprint: 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 Invarium. Nothing to install.
invarium_prepare_blueprint is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the invarium_prepare_blueprint 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 invarium_prepare_blueprint. 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_prepare_blueprint is provided by the Invarium MCP server (invarium-ai/invarium). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 Invarium 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.