Add the MCP connection or the official plugin.
Integrations
Connect your production traces to Flowlines.
Bring OpenTelemetry, Langfuse, or LangSmith. Keep your current provider. MCP servers use a separate standards-based instrumentation path.
Application agent traces
Keep your telemetry stack. Add cross-session analysis.
If your traces already contain enough session, user, call, and outcome context, Flowlines can analyze them without a proprietary application SDK.
Connection studio
Choose your source. See the exact path.
Switch between the supported production paths and see what moves, what stays, and how Flowlines fits.
keep the stack you already trust
Connection studioChoose a source
No trace migration requiredLive push
Send the traces you already emit.
Route standard OTLP traces to Flowlines while your current trace store stays in place.
- OTLP/JSON or protobuf
- Namespace API key
- Existing semantic attributes
01Your agent02OTLP exporter03Flowlines analysis
OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=https://api.flowlines.ai/v1/tracesIllustrative connection pathRead-only or push
Keep Langfuse as your trace system.
Poll one project read-only, or mirror the same spans through a second OpenTelemetry exporter.
- Read-only polling
- Second exporter option
- Sessions and users preserved
01Langfuse project02Scoped connection03Flowlines analysis
Connection scope: one project, read-onlyIllustrative connection pathRead-only or push
Add the cross-session view to LangSmith.
Read runs from one project or receive a mirrored stream through LangSmith OpenTelemetry export.
- Project-level scope
- OpenTelemetry export
- Threads become sessions
01LangSmith runs02Project connection03Flowlines analysis
Connection scope: one project, read-onlyIllustrative connection pathMCP server setup
Connect Flowlines. Ask to onboard.
Your assistant prepares and applies an OpenTelemetry plan, then checks the result. No proprietary SDK or extra tracing platform required.
Your own server. Your own data.
Start where you already work.
one connection, then your use case
Get a plan for the MCP server in your repository.
Your assistant adds OpenTelemetry instrumentation and runs the tests.
Ask Flowlines to verify the telemetry and fix any gaps.
How the layers fit
Debug individual runs. Monitor repeated behavior.
Langfuse and LangSmith remain useful for trace storage and call-level debugging. Flowlines adds cross-session behavioral analysis, user and intent rollups, recurring issue detection, and production outcomes.
Provider connections can remain read-only because Flowlines is the analysis layer.
100 MCP sessions a month, free