install_command
Canonical install command(s) across every package manager of the ecosystem (npm/pnpm/yarn/bun, pip/uv/poetry, cargo, go, composer, maven+gradle, nuget, …). USE WHEN: emitting an install line and you want correct flags. RETURNS: {primary, variants[]}.
This record as markdown: /tools/dev-depscope-mcp/install-command.md
What install_command does on Depscope
AI agents call install_command to retrieve information from Depscope without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
package | string | Yes | |
version | string | — | Optional explicit version; defaults to latest. |
ecosystem | string | Yes |
Parameters from the server's own tool schema.
Why install_command is rated Low
This tool retrieves and returns the correct install command syntax for various package managers. It does not execute any commands, modify any data, or trigger any external operations. It is purely informational, generating text that a user or agent could then choose to run separately. The blast radius of misuse is very low since no action is taken automatically.
From the tool's definition 'Canonical install command(s) across every package manager' and 'RETURNS: {primary, variants[]}' — the tool returns formatted install command strings, it does not execute them
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs install_command safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Depscope, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For install_command, this is the rule to start with:
install_command is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Depscope, apply this rule, and every install_command call is checked against it from then on.
Questions about install_command
Canonical install command(s) across every package manager of the ecosystem (npm/pnpm/yarn/bun, pip/uv/poetry, cargo, go, composer, maven+gradle, nuget, …). USE WHEN: emitting an install line and you want correct flags. RETURNS: {primary, variants[]}. It is categorised as a Read tool in the Depscope MCP Server, which means it retrieves data without modifying state.
install_command accepts 3 parameters: package, version, ecosystem. Required: package, ecosystem. The full parameter table on this page comes from the server's own tool schema.
Register the Depscope MCP server in PolicyLayer and add a rule for install_command: 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 Depscope. Nothing to install.
install_command is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the install_command 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 install_command. 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.
install_command is provided by the Depscope MCP server (cuttalo/depscope-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Depscope, and thousands of servers like it.
This server
Across the catalogue