Create a score for a trace or observation. Supports numeric, boolean, and categorical score types.
AI agents use createScore to create or update resources in Langfuse Mcp Extended — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Langfuse Mcp Extended environment.
This tool creates (Write operation) scoring data associated with traces or observations in Langfuse. It modifies state by adding a new score record but is reversible - scores can be updated or deleted via other tools on the server (deleteScore exists). The impact is contained to scoring metadata rather than core data deletion.
From the tool's definition Tool name is 'createScore' with description stating 'Create a score' - explicit Create operation that adds new data to a trace/observation record without irreversible deletion.
Attacks that exploit this kind of access
Create a score for a trace or observation. Supports numeric, boolean, and categorical score types. It is categorised as a Write tool in the Langfuse Mcp Extended MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Langfuse Mcp Extended MCP server in PolicyLayer and add a rule for createScore: 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.
createScore is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the createScore 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 createScore. 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.
createScore 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 →