Build solutions, not workarounds.
What do you want Langfuse and Tilth to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny 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 can start in Tilth
When New Trace in Langfuse
then Find fertiliser divergence in Tilth
When New Trace in Langfuse
then Find fertiliser estimate history in Tilth
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 Tilth
Triggers and actions 1 trigger · 20 actions
Trigger
New TracePolling trigger: fires for newly created traces (dedup by trace id / timestamp).
Action
Add CommentAdd a comment to a trace/observation/session/prompt object.
Action
Add DatasetCreate a new dataset.
Action
Add Dataset ItemCreate an item (input/expected_output/metadata) in a dataset.
Action
Add PromptCreate a new prompt version (text or chat).
Action
Add ScoreCreate a score attached to a trace/observation/session (numeric, categorical, or boolean).
Action
Delete TraceDelete a trace by id.
Action
Get ProjectReads the Langfuse project that the connection's project-scoped API key belongs to.
Action
Get PromptGet a prompt by name (and optional version/label).
Action
Get TraceGet a single trace by id, including nested observations/scores.
Action
List Dataset ItemsList items in a dataset.
Action
List DatasetsList all datasets in the project.
Action
List PromptsList all prompts in the project.
Action
List ScoresList scores with optional filters.
Action
Find fertiliser divergencePer-day forward-error time series for one or all fertiliser grades, showing how far the daily estimate was from the next weekly market print.
Action
Find fertiliser estimate historyRecent estimate history (the "nowcast line") for one product, newest-first, capped at 400 rows.
Action
Find fertiliser price seriesCurated AHDB price series (date + price + cadence) for a product, newest-first, capped at 70 prices.
Action
Get fertiliser index comparisonRebased overlay of the daily forecast vs the official DEFRA index for a product, consistency + lead-time only.
Action
Get fertiliser narrativeRanked market facts for a product's SEO narrative and authoritative display range, computed server-side.
Action
Get fertiliser overviewMarket-wide weekly aggregate for the hub page — how many grades rose, the biggest mover.
Action
List fertiliser estimatesLatest price estimate per fertiliser product with track record.
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 MailchimpMailchimp marketing automation and email platform.
Langfuse to StripeStripe is a payment processing platform for online businesses.
Langfuse to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Langfuse to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
Langfuse to PipedrivePipedrive is a sales CRM and pipeline management tool.
Langfuse to NotionA new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team.
More into Tilth
HubSpot to TilthHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to TilthSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to TilthSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to TilthGoogle Sheets
Gmail to TilthGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to TilthGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Langfuse and Tilth, 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 Tilth when something happens in Langfuse?
Any of Tilth's 7 actions, including Find fertiliser divergence, Find fertiliser estimate history, Find fertiliser price series and Get fertiliser index comparison. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Tilth to Langfuse?
Tilth has no triggers in the catalog today, so automations start in Langfuse. If you need the other direction, ask: your agent reads Tilth's API documentation and adds it.
Do I have to build a connector for Langfuse or Tilth?
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.
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.