AI agents call stash-list to retrieve information from Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns stash metadata (index, message, date, branch, file summaries) without modifying, deleting, or executing any operations. It has no side effects and poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'stash-list' and description 'Lists all stash entries' indicates a retrieval operation. The verb 'Lists' and the action of returning structured data without modification confirm read-only behavior.
Attacks that exploit this kind of access
Lists all stash entries with index, message, date, branch, and optional file change summary. Returns structured stash data. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.
Register the Python MCP server in PolicyLayer and add a rule for stash-list: 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.
stash-list 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 stash-list 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 stash-list. 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.
stash-list 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.
stash-list 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 →