run_kernel_vm
Run a ChainGraph decision kernel's compute(policy_parameters) inside a sandboxed, deterministic, in-browser QuickJS-ng WebAssembly VM (ocg-deterministic-compute@2) and return its output_payload. Demo kernel set only -- for the full catalog, use the worker's compute kernels directly. Renders the i...
This record as markdown: /tools/postoaklabs-ainumbers-mcp-apps/run-kernel-vm.md
What run_kernel_vm does on Ainumbers Mcp Apps
AI agents invoke run_kernel_vm to trigger actions in Ainumbers Mcp Apps. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
inputs | object | — | Map of tool input element IDs to values (see manifest input_schema). Applied via AIN Bridge prefill. |
Parameters from the server's own tool schema.
Why run_kernel_vm is rated High
This tool executes code (a decision kernel computation) in response to user-provided parameters. Although sandboxed and deterministic, it is fundamentally an Execute category tool because it triggers external computation operations whose side effects and outputs depend entirely on the arguments supplied.
From the tool's definition Tool executes arbitrary code via 'Run a ChainGraph decision kernel's compute(policy_parameters) inside a sandboxed...WebAssembly VM' and 'returns its output_payload'.
Attacks that exploit this kind of access
The rule that runs run_kernel_vm safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ainumbers Mcp Apps, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_kernel_vm, this is the rule to start with:
run_kernel_vm stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Ainumbers Mcp Apps, apply this rule, and every run_kernel_vm call is checked against it from then on.
Questions about run_kernel_vm
Run a ChainGraph decision kernel's compute(policy_parameters) inside a sandboxed, deterministic, in-browser QuickJS-ng WebAssembly VM (ocg-deterministic-compute@2) and return its output_payload. Demo kernel set only -- for the full catalog, use the worker's compute kernels directly. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network). It is categorised as a Execute tool in the Ainumbers Mcp Apps MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_kernel_vm accepts 1 parameter: inputs. The full parameter table on this page comes from the server's own tool schema.
Register the Ainumbers Mcp Apps MCP server in PolicyLayer and add a rule for run_kernel_vm: 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 Ainumbers Mcp Apps. Nothing to install.
run_kernel_vm 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 run_kernel_vm 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 run_kernel_vm. 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.
run_kernel_vm is provided by the Ainumbers Mcp Apps MCP server (postoaklabs/ainumbers-mcp-apps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ainumbers Mcp Apps, and thousands of servers like it.
Across the catalogue