List all datasets in the project.
AI agents call listDatasets to retrieve information from Langfuse Mcp Extended without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a collection of datasets from the Langfuse project for inspection or reference. It performs no modification, deletion, execution, or financial transaction. It is a straightforward enumeration endpoint with no state-changing effects.
From the tool's definition Tool name is 'listDatasets' and description states 'List all datasets in the project.' The verb 'list' is a canonical read-only operation that retrieves and queries data without side effects.
Attacks that exploit this kind of access
List all datasets in the project. It is categorised as a Read tool in the Langfuse Mcp Extended MCP Server, which means it retrieves data without modifying state.
Register the Langfuse Mcp Extended MCP server in PolicyLayer and add a rule for listDatasets: 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 Langfuse Mcp Extended. Nothing to install.
listDatasets 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 listDatasets 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 listDatasets. 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.
listDatasets is provided by the Langfuse Mcp Extended MCP server (langfuse-mcp-extended). 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 →