list_scores_v2
Retrieve Langfuse scores with optional filters for name, trace, value, source, and timestamps to analyze LLM evaluation results.
Instructions
List scores via Scores API v3 with optional filters (GET /v2/scores where v3 is not served).
With operator ``=`` and a value, v3 defaults an omitted data_type to NUMERIC; pass BOOLEAN for boolean scores.
Strict ``>``/``<`` can return fewer than limit rows on a page after boundary rows are dropped; next_page shows whether more rows exist.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Optional score name filter | |
| page | No | Page number for pagination (starts at 1) | |
| limit | No | Items per page (max 100) | |
| value | No | Optional numeric score value filter | |
| source | No | Optional score source filter | |
| user_id | No | Optional user ID filter (Scores API v3 has none: uses GET /v2/scores, which Langfuse Cloud removes on 2026-11-16) | |
| operator | No | Optional comparison for value: =, >, >=, < or <= (default =) | |
| queue_id | No | Optional annotation queue ID | |
| trace_id | No | Optional trace ID | |
| config_id | No | Optional score config ID | |
| data_type | No | Optional score data type | |
| score_ids | No | Optional comma-separated score IDs | |
| session_id | No | Optional session ID (not together with trace_id) | |
| trace_tags | No | Optional comma-separated trace tags (Scores API v3 has none: uses GET /v2/scores, which Langfuse Cloud removes on 2026-11-16) | |
| environment | No | Optional environment filter | |
| to_timestamp | No | Optional ISO8601 timestamp upper bound | |
| from_timestamp | No | Optional ISO8601 timestamp lower bound |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||