AI agents invoke add-package to trigger actions in Python. 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 an external dotnet CLI command to add a NuGet package. The explicit warning about executing untrusted code elevates severity. While it modifies project files (Write), the arbitrary code execution risk during package installation makes Execute the correct category, with high severity due to potential for supply-chain attacks or malicious package execution.
From the tool's definition 'Runs dotnet add package' and 'WARNING: may execute untrusted code'
Attacks that exploit this kind of access
Runs dotnet add package to add a NuGet package and returns structured results. WARNING: may execute untrusted code. It is categorised as a Execute tool in the Python MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Python 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 Python. Nothing to install.
add-package 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 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 Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
add-package is one line of Python's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →