wsl_get_dataset
AI agents call wsl_get_dataset to retrieve information from Pypi:wsl Envidat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The naming pattern and server context (environmental data querying service) strongly indicate this is a retrieval tool. No sibling tools perform mutations or destructive operations. The 'get_' prefix combined with the read-only nature of the service and lack of side-effect capability justify Read category with high confidence. Low severity because environmental research data queries pose minimal risk of abuse.
From the tool's definition Tool named 'wsl_get_dataset' on a data query server (WSL/EnviDat) that exposes read-only environmental research data.
Attacks that exploit this kind of access
wsl_get_dataset. It is categorised as a Read tool in the Pypi:wsl Envidat MCP Server, which means it retrieves data without modifying state.
Register the Pypi:wsl Envidat MCP server in PolicyLayer and add a rule for wsl_get_dataset: 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:wsl Envidat. Nothing to install.
wsl_get_dataset 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 wsl_get_dataset 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 wsl_get_dataset. 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.
wsl_get_dataset is provided by the Pypi:wsl Envidat MCP server (pypi:wsl-envidat-mcp). 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 →