AI agents use update to create or update resources in Python — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Python environment.
This tool modifies dependency specifications in a lock file (e.g., poetry.lock, requirements.lock, etc.), which is a Write operation. While lock files are important for reproducibility, updates are reversible—they can be undone by reverting to a previous lock file state or running the update command again with different constraints.
From the tool's definition Tool description states it 'Updates dependencies in the lock file' and can 'update a single package', which modifies the lock file reversibly.
Attacks that exploit this kind of access
Updates dependencies in the lock file. Optionally updates a single package. It is categorised as a Write tool in the Python MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Python MCP server in PolicyLayer and add a rule for update: 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.
update 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 update 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 update. 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.
update 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.
update 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 →