Integration
Connect USGS Earthquake Hazards Program to Langfuse
When something happens in USGS Earthquake Hazards Program, your agent does the next thing in Langfuse. Describe it in plain language and the automation is built, tested on every branch and kept running.
Build it
What do you want USGS Earthquake Hazards Program and Langfuse to do together?
Describe it and your agent reads both APIs, builds the automation, tests every branch and ships it. The list below is what exists today, not the limit.
Ask the assistant
You'll sign in before anything runs. What you typed comes with you.
Or work from Claude Code
Install the APIANT plugin for Claude Code and build, edit, test and read run history from your terminal. Every plan gets this, including free, and it spends no assistant credits.
Connect Claude CodeEverything your agent can do with USGS Earthquake Hazards Program and Langfuse
Triggers and actions 2 triggers ยท 15 actions
Trigger
New earthquakePolling trigger over the real-time GeoJSON feed (e.g. https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/{significant|4.5|2.5|1.0|all}_hour.geojson, configurable magnitude threshold/window) or the FDSN query endpoint ordered by time-desc. Fires once per new event id (dedup on feature.id), delivering magnitude, place, time, coordinates, depth.
- Find earthquakes by magnitude
Search earthquake events via GET https://earthquake.usgs.gov/fdsnws/event/1/query?format=geojson with filters (starttime, endtime, minmagnitude, maxmagnitude, mindepth, maxdepth, latitude, longitude, maxradiuskm, alertlevel, eventtype, orderby, limit). Returns a GeoJSON FeatureCollection of matching events.
- Get earthquake
Fetch a single earthquake event's detail via GET https://earthquake.usgs.gov/fdsnws/event/1/query?format=geojson&eventid={eventid}. Returns the full GeoJSON Feature including magnitude, place, time, coordinates and depth.
Trigger
New TracePolling trigger: fires for newly created traces (dedup by trace id / timestamp). GET /api/public/traces
- Add Comment
Add a comment to a trace/observation/session/prompt object. POST /api/public/comments
- Add Dataset
Create a new dataset. POST /api/public/v2/datasets
- Add Dataset Item
Create an item (input/expected_output/metadata) in a dataset. POST /api/public/dataset-items
- Add Prompt
Create a new prompt version (text or chat). POST /api/public/v2/prompts
- Add Score
Create a score attached to a trace/observation/session (numeric, categorical, or boolean). POST /api/public/scores
- Delete Trace
Delete a trace by id. DELETE /api/public/traces/{traceId}
- 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 /api/public/v2/prompts/{promptName}
- Get Trace
Get a single trace by id, including nested observations/scores. GET /api/public/traces/{traceId}
- List Dataset Items
List items in a dataset. GET /api/public/dataset-items
- List Datasets
List all datasets in the project. GET /api/public/v2/datasets
- List Prompts
List all prompts in the project. GET /api/public/v2/prompts
- List Scores
List scores with optional filters. GET /api/public/v2/scores
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.