Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to Langfuse

Scalekit connector
Open markdown

The Langfuse connector lets your AI agent work with Langfuse. Scalekit handles authentication for every call, so your agent never handles credentials. It comes with 58 tools.

Tools
58
What they doRead · write · destructive
32 · 16 · 1032 read16 write10 destructive
Users sign in with

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv
  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>
  3. Create the Langfuse connection

    In AgentKit > Connections, create a Langfuse connection. The name you give it is the connection_name your code passes. See Configure connections.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • langfuse_annotation_queue_getGet one annotation queue.Read-only

    Get Annotation Queue

    Get one annotation queue. Returns its name, description and score configs.

    Inputs

    queue_idstringrequired
    ID of the annotation queue. Get it from langfuse_annotation_queues_list. Example: cm1q2w3e4r5t6y7u8i9o0p.
  • langfuse_annotation_queue_item_getGet one item of an annotation queue.Read-only

    Get Annotation Queue Item

    Get one item of an annotation queue. Returns the item's object, status and completion info.

    Inputs

    item_idstringrequired
    ID of the queue item. Example: cm2a3s4d5f6g7h8j9k0l1z.
    queue_idstringrequired
    ID of the annotation queue. Get it from langfuse_annotation_queues_list. Example: cm1q2w3e4r5t6y7u8i9o0p.
  • langfuse_annotation_queue_items_listList the items in an annotation queue, optionally by status, with paging.Read-only

    List Annotation Queue Items

    List the items in an annotation queue, optionally by status, with paging. Returns each item's ID, object (trace, observation or session), status and timestamps.

    Inputs

    queue_idstringrequired
    ID of the annotation queue. Get it from langfuse_annotation_queues_list. Example: cm1q2w3e4r5t6y7u8i9o0p.
    limitinteger
    Items per page. Example: 50.
    pageinteger
    Page number, starting at 1. Example: 1.
    statusstring
    Filter by status. Example: PENDING.one of PENDINGCOMPLETED
  • langfuse_annotation_queues_listList annotation queues, with paging.Read-only

    List Annotation Queues

    List annotation queues, with paging. Returns each queue's ID, name, description and score configs.

    Inputs

    limitinteger
    Items per page. Example: 50.
    pageinteger
    Page number, starting at 1. Example: 1.
  • langfuse_comment_getGet one comment.Read-only

    Get Comment

    Get one comment. Returns its object, content, author and time.

    Inputs

    comment_idstringrequired
    The unique langfuse identifier of a comment. Example: cm3x4c5v6b7n8m9q0w1e2r.
  • langfuse_comments_listList comments, optionally on one object, with paging.Read-only

    List Comments

    List comments, optionally on one object, with paging. Returns each comment's ID, object, content, author and time.

    Inputs

    author_user_idstring
    Filter comments by author user id. Example: user-1.
    limitinteger
    Items per page. Example: 50.
    object_idstring
    Filter comments by object id. If objectType is not provided, an error will be thrown. Example: 4bf92f3577b34da6a3ce929d0e0e4736.
    object_typestring
    Filter comments by object type (trace, observation, session, prompt). Example: TRACE.
    pageinteger
    Page number, starting at 1. Example: 1.
  • langfuse_dataset_getGet one dataset by name.Read-only

    Get Dataset

    Get one dataset by name. Returns the dataset's ID, description and metadata.

    Inputs

    dataset_namestringrequired
    Dataset Name. Example: golden-qa.
  • langfuse_dataset_item_getGet one dataset item.Read-only

    Get Dataset Item

    Get one dataset item. Returns its input, expected output, metadata, status and source.

    Inputs

    dataset_item_idstringrequired
    ID of the dataset item. Example: item-001.