Run pnpm install at the workspace root or limited to filtered packages.
AI agents invoke pnpm_install to trigger actions in Promethean OS MCP. 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.
This tool executes the pnpm package manager to install dependencies. It runs an external shell command that modifies the filesystem (node_modules, lockfiles) and can trigger lifecycle scripts (postinstall hooks), making it an Execute-category action. Misuse could introduce malicious packages or trigger arbitrary code via install scripts.
From the tool's definition "Run pnpm install at the workspace root or limited to filtered packages"
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Run pnpm install at the workspace root or limited to filtered packages. It is categorised as a Execute tool in the Promethean OS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Promethean OS MCP server in PolicyLayer and add a rule for pnpm_install: 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 Promethean OS MCP. Nothing to install.
pnpm_install 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 pnpm_install 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 pnpm_install. 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.
pnpm_install is provided by the Promethean OS MCP server (octave-commons/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →