shell
Makes packages available in the environment and optionally runs a command. Returns stdout, stderr, exit code, and duration.
This record as markdown: /tools/io-github-dave-london-cargo/shell.md
What shell does on Cargo
AI agents invoke shell to trigger actions in Cargo. 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.
Why shell is rated High
The tool explicitly runs commands and returns execution results (stdout, stderr, exit code). This is a general-purpose shell execution primitive with no apparent restrictions on what commands can be run. An AI agent could use this to run any arbitrary command, making it critical severity due to the unlimited blast radius — data exfiltration, system modification, destructive operations, and more are all possible.
From the tool's definition 'optionally runs a command' and 'Returns stdout, stderr, exit code, and duration' — this tool executes arbitrary shell commands in the environment
Attacks that exploit this kind of access
The rule that runs shell safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cargo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For shell, this is the rule to start with:
shell 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 Cargo, apply this rule, and every shell call is checked against it from then on.
Questions about shell
Makes packages available in the environment and optionally runs a command. Returns stdout, stderr, exit code, and duration. It is categorised as a Execute tool in the Cargo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cargo MCP server in PolicyLayer and add a rule for shell: 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 Cargo. Nothing to install.
shell 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 shell 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 shell. 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.
shell is provided by the Cargo MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cargo, and thousands of servers like it.
Across the catalogue