Pakkawork
All integrations
LA
Catalogue metadata onlydeveloper toolsv00000000_00

LANGFUSE

Langfuse

Open source LLM engineering platform. Traces, evals, prompt management and metrics to debug and improve your LLM application.

Description is untrusted, display-only upstream metadata. It never becomes policy, OAuth scope authority, or an agent instruction.

Pakkawork boundary

Research catalogue metadata only. No Pakkawork OAuth, credential, host, quota, executor, or verifier is enabled.

No Pakkawork execution adapter is enabled. Hosted account-authorisation availability is workspace-specific and checked separately in the dashboard.Check workspace connection options
Attributed source

13

Action summaries

Display-only definitions

0

Trigger types

Not installed instances

1

Auth modes

Field names, never values

No

Execution

No runtime adapter

Authentication map

What setup is declared?

Only field names, types, and required markers are shown. Secret values, default auth URLs, credential material, and inferred OAuth scopes are excluded.
API_KEY

API_KEY

langfuse_api_key

Provider setup

Developer setup

No fields declared in this snapshot.

User connection

  • Public Keyusername · stringRequired
  • Secret Keypassword · stringRequired
  • Region or Base URLregion · stringOptional

Capability index

Actions and trigger definitions

Static summaries are available. Live schemas remain disabled until PROVIDER_HUB_API_KEY is configured server-side.
Actions (13)Triggers (0)

Showing 1–13 of 13 actions

Create Score

LANGFUSE_CREATE_SCORE

Attach an evaluation score to exactly one Langfuse trace, session, or dataset run, optionally narrowing a trace score to an observation.

Untrusted display-only summary

Get Annotation Queue

LANGFUSE_GET_ANNOTATION_QUEUE

Retrieve one Langfuse annotation queue by its ID.

Untrusted display-only summary

Get Prompt

LANGFUSE_GET_PROMPT

Retrieve a Langfuse text or chat prompt by name, deployment label, or exact version, with optional dependency resolution.

Untrusted display-only summary

List Annotation Queues

LANGFUSE_LIST_ANNOTATION_QUEUES

List annotation queues configured for human evaluation in the connected Langfuse project.

Untrusted display-only summary

List Dataset Items

LANGFUSE_LIST_DATASET_ITEMS

List dataset items, optionally scoped to a dataset, source trace or observation, or historical dataset version.

Untrusted display-only summary

List Dataset Run Items

LANGFUSE_LIST_DATASET_RUN_ITEMS

List run items for a specific Langfuse dataset and run name.

Untrusted display-only summary

List Datasets

LANGFUSE_LIST_DATASETS

List datasets available to the connected Langfuse project.

Untrusted display-only summary

List Experiments

LANGFUSE_LIST_EXPERIMENTS

List Langfuse experiments active in a required time range, optionally including metadata and directly attached scores.

Untrusted display-only summary

List Models

LANGFUSE_LIST_MODELS

List Langfuse-managed and project-custom model pricing definitions used for usage and cost calculation.

Untrusted display-only summary

List Observations

LANGFUSE_LIST_OBSERVATIONS

Search Langfuse observations such as generations, spans, events, agents, and tool calls, selecting only the field groups needed.

Untrusted display-only summary

List Scores

LANGFUSE_LIST_SCORES

Search numeric, boolean, categorical, text, and correction scores with subject and annotation context.

Untrusted display-only summary

Query Metrics

LANGFUSE_QUERY_METRICS

Run an aggregate Langfuse metrics query over observations or numeric, boolean, or categorical scores.

Untrusted display-only summary

Upsert LLM Connection

LANGFUSE_UPSERT_LLM_CONNECTION

Create or update a Langfuse LLM provider connection by provider name.

Untrusted display-only summary

Provenance

Versioned facts, explicit trust.

The detail snapshot comes from an attributed MIT-licensed repository revision. Safe local icons use exact-match CC0 Simple Icons symbols; unmatched brands use monograms.

Repository
https://github.com/provider-directoryHQ/provider-directory
Commit
85e33f6a81dfe987f6fc3637d48d45052cea8ca5
Generated
2026-09-12
Trust policy
untrusted_display_only

Remote text is plain display metadata only. It must never become an agent prompt, execution policy, OAuth grant, or executable instruction.