This record as markdown: /tools/io-github-dave-london-npm/shell.md
What shell does on Npm
AI agents invoke shell to trigger actions in Npm. 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 stdout/stderr/exit code, which is the hallmark of shell command execution. An AI agent could use this to run arbitrary system commands, making it critical severity. The 'makes packages available' aspect is secondary to the general command execution capability.
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 Npm, 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 Npm, 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 Npm MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Npm 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 Npm. 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 Npm 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 Npm, and thousands of servers like it.
This server
Across the catalogue