Get LLM generations/spans with details and filtering.
AI agents call get_observations to retrieve information from Langfuse MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries trace observations (LLM generations and spans) from Langfuse without modifying, executing, or deleting data. It is a straightforward data retrieval operation with no side effects, consistent with the Read category. The filtering capability does not change this classification as filters are applied to query results, not to modify underlying data.
From the tool's definition Tool name 'get_observations' and description 'Get LLM generations/spans with details and filtering' indicate retrieval of existing data with filtering capabilities.
Attacks that exploit this kind of access
Get LLM generations/spans with details and filtering. It is categorised as a Read tool in the Langfuse MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Langfuse MCP Server MCP server in PolicyLayer and add a rule for get_observations: 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 Server. Nothing to install.
get_observations 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 get_observations 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 get_observations. 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.
get_observations is provided by the Langfuse MCP Server MCP server (therealsachin/langfuse-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 →