Add package to pyproject.toml and update the virtual environment. Returns True if successful.
AI agents use add_package to create or update resources in Venv — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Venv environment.
This is a Write operation because it creates or modifies data (pyproject.toml) and environment state reversibly. While package additions can have side effects (installing dependencies with potential security implications), the operation itself is reversible via remove_package.
From the tool's definition The tool 'add_package' modifies pyproject.toml and updates the virtual environment. The description states it 'Add[s] package to pyproject.toml and update[s] the virtual environment', indicating creation/modification of configuration and environment state.
Documented attack patterns abuse exactly the kind of access add_package gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Venv, and nothing reaches the server without passing your rules. This is the rule we recommend for add_package:
{
"version": "1",
"default": "deny",
"tools": {
"add_package": {
"limits": [
{
"counter": "add_package_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_package stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add package to pyproject.toml and update the virtual environment. Returns True if successful. It is categorised as a Write tool in the Venv MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Venv MCP server in PolicyLayer and add a rule for add_package: 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 Venv. Nothing to install.
add_package 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 add_package 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 add_package. 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.
add_package is provided by the Venv MCP server (sparfenyuk/venv-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Venv, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Venv tools catalogued and risk-classified — across an index of 43,000+ MCP servers.