Add dependencies via pnpm, optionally scoped to specific workspace packages.
AI agents use pnpm_add to create or update resources in Promethean OS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Promethean OS MCP environment.
This tool creates or modifies package.json and lock files by adding dependencies—a reversible write operation. It does not execute arbitrary code (Execute category) or permanently delete data (Destructive). While it could indirectly affect system behavior if malicious packages are injected, the primary action is data modification.
From the tool's definition Tool name is 'pnpm_add' and description states 'Add dependencies via pnpm', indicating it modifies the package manifest and dependency tree by creating/adding entries.
Attacks that exploit this kind of access
Add dependencies via pnpm, optionally scoped to specific workspace packages. It is categorised as a Write tool in the Promethean OS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Promethean OS MCP server in PolicyLayer and add a rule for pnpm_add: 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_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pnpm_add 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_add. 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_add 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 →