engine_bundle
Full pipeline: import credentials from file → map to services → create encrypted .0n bundle. Combines engine_import + engine_export in one step. Example: engine_bundle({ source:
This record as markdown: /tools/io-github-0nork-0nmcp/engine-bundle.md
What engine_bundle does on 0nmcp
AI agents use engine_bundle to create or update resources in 0nmcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 0nmcp environment.
Why engine_bundle is rated Medium
The tool creates and exports encrypted credential bundles, which modifies the system state by generating new files/artifacts. However, it does not irreversibly delete data (ruling out Destructive), does not move money (ruling out Financial), and does not execute arbitrary code (Execute would require actual command/script execution).
From the tool's definition engine_bundle creates encrypted .0n bundle from credentials; description states 'import credentials from file → map to services → create encrypted .0n bundle'. This is a write operation that generates new data artifacts and persists them.
Attacks that exploit this kind of access
The rule that runs engine_bundle safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 0nmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For engine_bundle, this is the rule to start with:
engine_bundle stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 0nmcp, apply this rule, and every engine_bundle call is checked against it from then on.
Questions about engine_bundle
Full pipeline: import credentials from file → map to services → create encrypted .0n bundle. Combines engine_import + engine_export in one step. Example: engine_bundle({ source:. It is categorised as a Write tool in the 0nmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the 0n MCP server in PolicyLayer and add a rule for engine_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 0nmcp. Nothing to install.
engine_bundle is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the engine_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.
Set action: deny in the PolicyLayer policy for engine_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.
engine_bundle is provided by the 0n MCP server (0nmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 0n, and thousands of servers like it.
This server
Across the catalogue