Create or upsert a dataset item. Use id parameter for idempotent updates.
AI agents use createDatasetItem 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 or updates data in a dataset, which is a reversible operation (can be modified or deleted later via deleteDatasetItem). It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition "Create or upsert a dataset item" - the tool creates new data or modifies existing dataset items reversibly using the id parameter for idempotent updates.
Attacks that exploit this kind of access
Create or upsert a dataset item. Use id parameter for idempotent updates. 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 createDatasetItem: 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.
createDatasetItem 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 createDatasetItem 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 createDatasetItem. 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.
createDatasetItem 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 →