audit_bundle

Generate a single non-destructive audit payload with config, session, report, candidates, dry-run metrics and safety metadata.

Server Clean Process Ended marcelocaporale/clean-process-ended
Category Read
Risk class Low
Parameters 00 required

What audit_bundle does on Clean Process Ended

AI agents call audit_bundle to retrieve information from Clean Process Ended without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why audit_bundle needs a policy

The tool aggregates configuration, session data, reports, candidates, and dry-run metrics into a read-only audit bundle. It is explicitly described as non-destructive, meaning no side effects, writes, or deletions occur. This is purely a data retrieval and reporting operation.

From the tool's definition 'non-destructive audit payload' and 'dry-run metrics and safety metadata' — the tool explicitly states it only generates/reads audit information without modifying or deleting anything

Questions about audit_bundle

What does the audit_bundle tool do? +

Generate a single non-destructive audit payload with config, session, report, candidates, dry-run metrics and safety metadata. It is categorised as a Read tool in the Clean Process Ended MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on audit_bundle? +

Register the Clean Process Ended MCP server in PolicyLayer and add a rule for audit_bundle: 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 Clean Process Ended. Nothing to install.

What risk level is audit_bundle? +

audit_bundle is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit audit_bundle? +

Yes. Add a rate_limit block to the audit_bundle 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.

How do I block audit_bundle completely? +

Set action: deny in the PolicyLayer policy for audit_bundle. 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.

What MCP server provides audit_bundle? +

audit_bundle is provided by the Clean Process Ended MCP server (marcelocaporale/clean-process-ended). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.