shells_execShell
Run one command in a Shell (POST /v1/shells/shells/{id}/exec)
This record as markdown: /tools/onesi-genesis-mcp/shells-execshell.md
What shells_execShell does on Genesis
AI agents invoke shells_execShell to trigger actions in Genesis. 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 |
|---|---|---|---|
id | string | Yes | The Shell's id (an Omega deployment UUID) |
body | object | Yes | |
idempotency_key | string | Yes | Stable key (required); reuse it to replay instead of acting twice |
Parameters from the server's own tool schema.
Why shells_execShell is rated High
shells_execShell triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts file system path (body.cwd) · Accepts raw HTML/template content (body)
Attacks that exploit this kind of access
The rule that runs shells_execShell safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Genesis, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For shells_execShell, this is the rule to start with:
shells_execShell 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 Genesis, apply this rule, and every shells_execShell call is checked against it from then on.
Questions about shells_execShell
Run one command in a Shell (POST /v1/shells/shells/{id}/exec). It is categorised as a Execute tool in the Genesis MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
shells_execShell accepts 3 parameters: id, body, idempotency_key. Required: id, body, idempotency_key. The full parameter table on this page comes from the server's own tool schema.
Register the Genesis MCP server in PolicyLayer and add a rule for shells_execShell: 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 Genesis. Nothing to install.
shells_execShell 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 shells_execShell 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 shells_execShell. 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.
shells_execShell is provided by the Genesis MCP server (@onesi/genesis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Genesis, and thousands of servers like it.
Across the catalogue