--- title: "Connect Langfuse and LaunchDarkly - APIANT.ai" description: "When \"New Trace\" fires in Langfuse, your agent runs \"Create a project\" in LaunchDarkly." canonical: "https://apiant.ai/connect/langfuse-to-launchdarkly" --- # Connect Langfuse and LaunchDarkly When **New Trace** fires in [Langfuse](https://apiant.ai/connections/langfuse), your agent runs **Create a project** in [LaunchDarkly](https://apiant.ai/connections/launchdarkly), or **Access Token Event** in LaunchDarkly to **Add Comment** in Langfuse. Describe the whole flow and it is built, tested on every scenario and kept running. Langfuse **1** trigger Langfuse **14** actions LaunchDarkly **11** triggers LaunchDarkly **39** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Langfuse and LaunchDarkly to do together? Give your AI client this address. `https://mcp.apiant.ai` One 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.ai` Start Claude Code there, approve the server, and sign in in the browser page it opens. [Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### Zed Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) Example flows ## What Langfuse and LaunchDarkly can do together ### From Langfuse to LaunchDarkly - When **New Trace** in Langfuse then **Create a project** in LaunchDarkly - When **New Trace** in Langfuse then **Create a feature flag** in LaunchDarkly ### From LaunchDarkly to Langfuse - When **Access Token Event** in LaunchDarkly then **Add Comment** in Langfuse - When **Code Reference Repository Event** in LaunchDarkly then **Add Dataset Item** in 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 LaunchDarkly ## Triggers and actions 12 triggers · 53 actions - Trigger **New Trace** Polling trigger: fires for newly created traces (dedup by trace id / timestamp). - Action **Add Comment** Add a comment to a trace/observation/session/prompt object. - Action **Add Dataset** Create a new dataset. - Action **Add Dataset Item** Create an item (input/expected_output/metadata) in a dataset. - Action **Add Prompt** Create a new prompt version (text or chat). - Action **Add Score** Create a score attached to a trace/observation/session (numeric, categorical, or boolean). - Action **Delete Trace** Delete a trace by id. - Action **Get Project** Reads the Langfuse project that the connection's project-scoped API key belongs to. - Action **Get Prompt** Get a prompt by name (and optional version/label). - Action **Get Trace** Get a single trace by id, including nested observations/scores. - Action **List Dataset Items** List items in a dataset. - Action **List Datasets** List all datasets in the project. - Action **List Prompts** List all prompts in the project. - Action **List Scores** List scores with optional filters. - Action **List Traces** List traces with optional filters (user, session, tags, timerange). - Trigger **Access Token Event** Triggers when access token activity happens on your LaunchDarkly account. - Trigger **Code Reference Repository Event** Triggers when code reference repository activity happens on your LaunchDarkly account. - Trigger **Flag Event** Triggers when flag activity happens on your LaunchDarkly account. - Trigger **Integration Event** Triggers when integration activity happens on your LaunchDarkly account. - Trigger **Member Event** Triggers when member activity happens on your LaunchDarkly account. - Trigger **Relay Proxy Configuration Event** Triggers when relay proxy configuration activity happens on your LaunchDarkly account. - Trigger **Role Event** Triggers when role activity happens on your LaunchDarkly account. - Trigger **Segment Event** Triggers when segment activity happens on your LaunchDarkly account. - Trigger **Service Token Event** Triggers when service token activity happens on your LaunchDarkly account. - Trigger **Team Event** Triggers when team activity happens on your LaunchDarkly account. - Trigger **User Event** Triggers when user activity happens on your LaunchDarkly account. - Action **Add or Remove User Targets From a Feature Flag** Adds people to, or removes them from, the individual targeting list for one variation of a feature flag in a chosen environment. - Action **Create a feature flag** Creates a new feature flag in a LaunchDarkly project, either a plain on/off flag or one with your own list of variations. - Action **Create a metric** Creates a metric in a LaunchDarkly project so you can measure the effect of a flag or experiment - a custom event, a click, a page view, or a trace. - Action **Create an access token** Creates a LaunchDarkly API access token with the access level you choose. The full token value is returned only on this call, so save it right away. - Action **Create an environment** Adds a new environment to a LaunchDarkly project, so flags can be configured separately for it. Returns the environment's SDK keys. - Action **Create a project** Creates a new LaunchDarkly project, optionally with its own environments and flag-naming rules. - Action **Create a segment** Creates a segment in one environment of a LaunchDarkly project, so you can target a named group of people with your flags. - Action **Delete environment** Deletes an environment from a LaunchDarkly project, along with all the flag settings it held. - Action **Delete feature flag** Permanently deletes a feature flag from a LaunchDarkly project, in every environment. - Action **Delete metric** Deletes a metric from a LaunchDarkly project. - Action **Delete project** Deletes a LaunchDarkly project and everything inside it - all of its environments, flags and segments. - Action **Delete segment** Deletes a segment from one environment of a LaunchDarkly project. - Action **Evaluate a Feature Flag** Works out which variation of each feature flag a particular person (or other context) would be served in one environment, and why. - Action **Get access token** Returns one LaunchDarkly access token by its id, including its name, role, and when it was last used. - Action **Get custom role** Returns one LaunchDarkly custom role by its key, including its name, description, and policy statements. - Action **Get environment** Returns one environment in a LaunchDarkly project, including its keys, colour, and default flag settings. - Action **Get feature flag** Returns one feature flag in a LaunchDarkly project, including its variations, tags, and per-environment settings. - Action **Get metric** Returns one metric in a LaunchDarkly project, including how it is measured and which events it counts. - Action **Get project** Returns one LaunchDarkly project by its key, including its name, tags, and default settings. - Action **Get segment** Returns one segment in a LaunchDarkly project environment, including its included and excluded contexts and its rules. - Action **Get team** Returns one LaunchDarkly team by its key, including its name, description, and how many members and roles it has. - Action **List access tokens** Returns the access tokens in your LaunchDarkly account. - Action **List custom roles** Returns the custom roles in your LaunchDarkly account. - Action **List environments** Returns the environments in one LaunchDarkly project. - Action **List feature flags** Returns the feature flags in one LaunchDarkly project. - Action **List metrics** Returns the metrics in one LaunchDarkly project. - Action **List projects** Returns the projects in your LaunchDarkly account. - Action **List segments** Returns the segments in one LaunchDarkly project environment. - Action **List teams** Returns the teams in your LaunchDarkly account. - Action **List users** Returns the end users LaunchDarkly has seen in one project environment. Built on the contexts API, which replaced the retired users API. - Action **Search contexts** Searches the contexts LaunchDarkly has seen in one project environment using a filter expression. - Action **Toggle a Feature Flag** Turns a LaunchDarkly feature flag on or off in one environment. - Action **Update a Feature Flag With JSON** Updates a LaunchDarkly feature flag by sending your own semantic patch instructions as JSON, for changes the ready-made actions do not cover. - Action **Update custom role** Updates a LaunchDarkly custom role — its name, description, base permissions, or policy statements. Fields you leave blank are not changed. - Action **Update environment** Updates an environment in a LaunchDarkly project — its name, colour, cache time, or confirmation settings. Fields you leave blank are not changed. - Action **Update metric** Updates a metric in a LaunchDarkly project — its name, description, tags, or unit. Fields you leave blank are not changed. - Action **Update project** Updates a LaunchDarkly project — its name, tags, or default flag settings. Fields you leave blank are not changed. - Action **Update segment** Updates a segment in a LaunchDarkly project environment — its name, description, tags, or the contexts it includes and excludes. Fields you leave blank are not changed. - Action **Update team** Updates a LaunchDarkly team — its name, description, members, or custom roles. Fields you leave blank are not changed. ## Each app on its own - [ **Langfuse** Langfuse is an open-source LLM engineering platform (GitHub) that helps teams collaboratively debug...](https://apiant.ai/connections/langfuse) - [ **LaunchDarkly** LaunchDarkly allows you to innovate faster, deploy fearlessly, and make each release a masterpiece.](https://apiant.ai/connections/launchdarkly) Reviews ## What our customers say ## More from Langfuse - [ **Langfuse to 5DollarFootball** Football fixtures, results, standings and historical odds with corner and card lines](https://apiant.ai/connect/langfuse-to-5dollarfootball) - [ **Langfuse to Cloudflare Trace** Cloudflare Trace is a free JSON wrapper over Cloudflare's edge trace endpoint that reports what Cloudflare...](https://apiant.ai/connect/langfuse-to-cloudflare-trace) - [ **Langfuse to PaperClean** Clean document photos for printing, remove shadows, fix lighting](https://apiant.ai/connect/langfuse-to-paperclean) - [ **Langfuse to Postman** Postman is a platform for building and testing APIs.](https://apiant.ai/connect/langfuse-to-postman) - [ **Langfuse to Rendobar** Hosted media processing over REST: transcode, caption, watermark video](https://apiant.ai/connect/langfuse-to-rendobar) - [ **Langfuse to Runpod** Cloud GPU platform for renting on-demand compute to train and deploy AI models, including serverless...](https://apiant.ai/connect/langfuse-to-runpod) ## More into LaunchDarkly - [ **HubSpot to LaunchDarkly** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-launchdarkly) - [ **Google Sheets to LaunchDarkly** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-launchdarkly) - [ **Gmail to LaunchDarkly** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-launchdarkly) - [ **Google Calendar to LaunchDarkly** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-launchdarkly) - [ **Google Drive to LaunchDarkly** Google Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...](https://apiant.ai/connect/google-drive-to-launchdarkly) - [ **Shopify to LaunchDarkly** Shopify is a commerce platform for online stores and retail point-of-sale.](https://apiant.ai/connect/shopify-to-launchdarkly) Questions ## Langfuse and LaunchDarkly, 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 LaunchDarkly when something happens in Langfuse? Any of LaunchDarkly's 39 actions, including Create a feature flag, Create a metric, Create an access token and Create an environment. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from LaunchDarkly to Langfuse? Yes. When something happens in LaunchDarkly, your agent can act in Langfuse too. This page covers both directions: LaunchDarkly's triggers and Langfuse's actions are listed here as well. ### ### Do I have to build a connector for Langfuse or LaunchDarkly? 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 LaunchDarkly 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.