Can Lyro train a model or upload images to a Roboflow dataset?

No. This toolkit covers workflow execution and inference-server inspection - Run Workflow, Validate Workflow, Get Server Info, Get Server Metrics. Training runs and dataset management stay in the Roboflow console.

How does Lyro know what inputs a workflow expects?

Describe Workflow Interface returns the inputs, outputs, and their types for a given workflow specification. Lyro reads that first so the values it passes to Run Workflow match what the pipeline was built to accept.

What does Lyro report when the inference server looks unhealthy?

Get Server Metrics returns Prometheus metrics covering inference statistics and server performance, and Get Server Info returns the server's version, name, and unique identifier - enough to tell a misconfigured workflow apart from a struggling server.

Why would a workflow fail on execution engine version?

A specification can target an engine version the server does not support. Get Execution Engine Versions lists the versions currently available for workflow processing, so Lyro can say which one to target rather than leaving it to trial and error.

Roboflow MCP integration

Runs a vision workflow on demand, validates a specification before it executes, and reports inference server health and metrics.

Connect Roboflow See all integrations

7actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Get server info
Lyro retrieves information about the Roboflow inference server. Operators monitor server health to catch issues early.
Validate workflow
Lyro checks a Roboflow workflow specification for errors before it runs. Teams catch configuration mistakes instead of failing mid-processing.
Run workflow
Lyro executes a Roboflow workflow with your provided inputs. Vision AI pipelines process images automatically instead of manual analysis.

See all 7 actions

How businesses use Roboflow + Lyro

Each card is one request a support team gets, and the Roboflow actions Lyro runs to close it.

Run a vision workflow on demand
Lyro reads the workflow's declared inputs, outputs, and types, then executes the specification with the values supplied in the conversation and returns what the pipeline produced.
Run WorkflowDescribe Workflow Interface
Catch a broken specification before it runs
Lyro checks a workflow definition against the block schema and validates its structure, so a syntax problem surfaces as an answer rather than as a failed inference run.
Validate WorkflowGet Workflow SchemaDescribe Workflow Interface
Answer whether the inference server is healthy
Lyro reads the server's identity and version alongside its Prometheus metrics, so a question about slow or failing inference gets current numbers rather than a guess.
Get Server InfoGet Server Metrics
Check which execution engine a workflow needs
Lyro lists the Execution Engine versions the workflows API supports and reads the current block schema, so a compatibility question is settled before an upgrade is attempted.
Get Execution Engine VersionsGet Workflow Schema

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Roboflow actions it has and picks the ones a request needs.

01
Connect Roboflow
Authorize the Roboflow account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Roboflow actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Roboflow · Lyro

Everything else about Roboflow

Setup, permissions, and the limits of what Lyro can do inside Roboflow.

No. This toolkit covers workflow execution and inference-server inspection - Run Workflow, Validate Workflow, Get Server Info, Get Server Metrics. Training runs and dataset management stay in the Roboflow console.

Every action available in Roboflow

All 7 actions your agent can call on Roboflow, straight from the live MCP connection.

Describe workflow interface
Describe the interface of a workflow specification.
Get execution engine versions
Retrieve available Execution Engine versions from Roboflow workflows API.
Get server info
Retrieve information about the Roboflow inference server.
Get server metrics
Retrieve Prometheus metrics from the Roboflow inference server.
Get workflow schema
Fetch the workflows block schema from Roboflow.
Run workflow
Run a workflow specification with provided inputs.
Validate workflow
Validate a Roboflow workflow specification before execution.