extract_dependencies
AI agents call extract_dependencies to retrieve information from Pypi:pypreset without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to parse or retrieve existing project dependencies without modifying, deleting, or executing operations. It fits the Read category (retrieves or queries data with no side effects). Severity is low because reading dependency metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'extract_dependencies' suggests reading/querying dependency information from a project. No description provided, but the function name indicates data retrieval with no side effects.
Attacks that exploit this kind of access
extract_dependencies. It is categorised as a Read tool in the Pypi:pypreset MCP Server, which means it retrieves data without modifying state.
Register the Pypi:pypreset MCP server in PolicyLayer and add a rule for extract_dependencies: 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 Pypi:pypreset. Nothing to install.
extract_dependencies 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 extract_dependencies 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 extract_dependencies. 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.
extract_dependencies is provided by the Pypi:pypreset MCP server (KaiErikNiermann/pypreset). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →