[Langfuse] List scores/evaluations with filters. Scores are attached to traces or observations.
AI agents call langfuse_list_scores to retrieve information from Shepherd MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval tool that queries existing evaluation scores from Langfuse observability data. It has no side effects, cannot modify or delete data, and poses minimal risk even if misused by an AI agent. The worst outcome would be exposure of existing score/evaluation data, which is already recorded in the system.
From the tool's definition Tool name contains 'list' and description states 'List scores/evaluations with filters' — a retrieval operation with no modification capability. Scores are merely queried, not created, modified, or deleted.
Attacks that exploit this kind of access
[Langfuse] List scores/evaluations with filters. Scores are attached to traces or observations. It is categorised as a Read tool in the Shepherd MCP MCP Server, which means it retrieves data without modifying state.
Register the Shepherd MCP server in PolicyLayer and add a rule for langfuse_list_scores: 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 Shepherd MCP. Nothing to install.
langfuse_list_scores 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 langfuse_list_scores 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 langfuse_list_scores. 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.
langfuse_list_scores is provided by the Shepherd MCP server (neuralis-in/shepherd-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 →