Integration
Connect Langfuse and Skyvern
When New Trace fires in Langfuse, your agent runs Create and Run a Task in Skyvern, or New or Updated Skyvern Workflow in Skyvern to Add Comment in Langfuse. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Langfuse and Skyvern to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Langfuse and Skyvern can do together
From Langfuse to Skyvern
When New Trace in Langfuse
then Create and Run a Task in Skyvern
From Skyvern to Langfuse
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Langfuse and Skyvern
Triggers and actions 2 triggers · 29 actions
- New Trace
Polling trigger: fires for newly created traces (dedup by trace id / timestamp).
- Add Comment
Add a comment to a trace/observation/session/prompt object.
- Add Dataset
Create a new dataset.
- Add Dataset Item
Create an item (input/expected_output/metadata) in a dataset.
- Add Prompt
Create a new prompt version (text or chat).
- Add Score
Create a score attached to a trace/observation/session (numeric, categorical, or boolean).
- Delete Trace
Delete a trace by id.
- Get Project
Reads the Langfuse project that the connection's project-scoped API key belongs to.
- Get Prompt
Get a prompt by name (and optional version/label).
- Get Trace
Get a single trace by id, including nested observations/scores.
- List Dataset Items
List items in a dataset.
- List Datasets
List all datasets in the project.
- List Prompts
List all prompts in the project.
- List Scores
List scores with optional filters.
- List Traces
List traces with optional filters (user, session, tags, timerange).
- New or Updated Skyvern Workflow
Triggers when a Skyvern workflow (agent) is created or a new version of it is saved.
- Add browser session
Creates a Skyvern browser session that persists across multiple task and workflow runs, and returns its session id and live-view link.
- Add credential
Creates a new stored credential (login, credit card or secret) in your Skyvern organization for use by tasks and agents.
- Add workflow
Creates a new Skyvern workflow (agent) from a JSON or YAML definition and returns the saved workflow.
- Cancel run
Cancels a running Skyvern task run or workflow run by its id.
- Create and Run a Task
Starts a Skyvern browser-automation task from a plain-language prompt and returns the new run, including its id, status and link in the Skyvern app.
- Create and Run Task V2
Starts a Skyvern 2.0 browser task from a natural-language prompt and returns the new run's id and status.
- Delete workflow
Deletes a Skyvern workflow (agent) by its ID.
- Get a Browser Session
Returns the details of a Skyvern browser session, including its status, browser address for connecting, downloaded files and recordings.
- Get a Task
Returns a Skyvern task run by its id, including its status, extracted output, downloaded files, recording and screenshots.
- Get a Task V2
Returns the status, output, recording and screenshots of a Skyvern task run.
- Get a Workflow
Returns a Skyvern workflow (agent) by its permanent id, including its blocks, parameters and settings.
- List credentials
Returns the credentials stored in your Skyvern organization, optionally filtered by vault, type or search text. Secrets are never included.
- List runs
Returns your organization's task and agent runs, newest first, optionally filtered by status, run type, agent, tags, failure category or a search term.
- List workflows
Returns the workflows (agents) in your Skyvern organization, optionally filtered by search text, folder, status or tags. Returns up to 100 workflows.
- Run a Workflow
Starts a run of one of your Skyvern workflows (agents) with the parameters you supply, and returns the new run's id, status and link.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Langfuse
Langfuse to 5DollarFootballFootball fixtures, results, standings and historical odds with corner and card lines
Langfuse to Cloudflare TraceCloudflare Trace is a free JSON wrapper over Cloudflare's edge trace endpoint that reports what Cloudflare...
Langfuse to PaperCleanClean document photos for printing, remove shadows, fix lighting
Langfuse to PostmanPostman is a platform for building and testing APIs.
Langfuse to RendobarHosted media processing over REST: transcode, caption, watermark video
Langfuse to RunpodCloud GPU platform for renting on-demand compute to train and deploy AI models, including serverless...
More into Skyvern
HubSpot to SkyvernHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to SkyvernSalesforce is a leading enterprise customer relationship management (CRM) platform.
Google Sheets to SkyvernGoogle Sheets
Gmail to SkyvernGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to SkyvernGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Google Drive to SkyvernGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
Questions
Langfuse and Skyvern, answered
What can start an automation from Langfuse?
Any of Langfuse's 1 trigger in the catalog, including New Trace. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Skyvern when something happens in Langfuse?
Any of Skyvern's 15 actions, including Create and Run a Task, Create and Run Task V2, Add browser session and Add credential. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Skyvern to Langfuse?
Yes. When something happens in Skyvern, your agent can act in Langfuse too. This page covers both directions: Skyvern's triggers and Langfuse's actions are listed here as well.
Do I have to build a connector for Langfuse or Skyvern?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Langfuse and Skyvern without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.