Install a new MCP server. Use package+command+args for direct package installation (e.g., npm packages), or just name for registry-based installation
AI agents invoke mcp_install to trigger actions in 1MCP Server. 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.
Installing a package executes installation scripts and potentially arbitrary code from the package, and adds a new MCP server to the aggregation layer. This goes beyond a simple write operation as it triggers execution of package manager commands and install scripts, potentially altering system state significantly.
From the tool's definition "Install a new MCP server" and "direct package installation (e.g., npm packages)"
Documented attack patterns abuse exactly the kind of access mcp_install gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 1MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for mcp_install:
{
"version": "1",
"default": "deny",
"tools": {
"mcp_install": {
"limits": [
{
"counter": "mcp_install_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}mcp_install 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.
Free to start. No card required.
Install a new MCP server. Use package+command+args for direct package installation (e.g., npm packages), or just name for registry-based installation. It is categorised as a Execute tool in the 1MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 1MCP Server MCP server in PolicyLayer and add a rule for mcp_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 1MCP Server. Nothing to install.
mcp_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 mcp_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 mcp_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.
mcp_install is provided by the 1MCP Server MCP server (1mcp-app/agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 1MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 1MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.