For the complete documentation index, see llms.txt. This page is also available as Markdown.

MCP Server

Connect Claude, Cursor, ChatGPT, Codex, or any MCP client to the Roboflow MCP server, and the tools it exposes.

Work on your Roboflow projects together with AI. Connect Claude Code (or any MCP-compatible agent) to your workspace. It can create projects, upload data, train models, build Workflows, and guide you through the visual steps in the Roboflow UI. You handle what you're best at (seeing, labeling, judging results), your agent handles the rest.

Demo

https://mcp.roboflow.com/

Adding MCP

The Roboflow MCP server uses OAuth for authentication - no API key needed. You'll be prompted to sign in to Roboflow on first use.

After you sign in, a consent page shows the email of the Roboflow account you use. To connect a different account, click "Use a different account". If your account has no Workspace yet, you set one up before you approve the connection.

Add Roboflow as a connector in your Claude account. Once connected, it works everywhere - Claude.ai, Claude Desktop, and Claude Code.

Add Roboflow to Claude - click the link, confirm, and you're done. You'll be prompted to sign in to Roboflow with OAuth on first use.

Claude Code CLI

Cursor

Install the Roboflow plugin from the Cursor marketplace, or run /add-plugin roboflow in Cursor. Either installs the MCP server along with Roboflow's skills. Sign in to Roboflow with OAuth on first use.

To configure the server manually instead, add this to Cursor's MCP config (~/.cursor/mcp.json):

ChatGPT

Open the Roboflow plugin listing and click "Install plugin". Sign in to Roboflow when ChatGPT asks.

Codex

ChatGPT and Codex share one plugin. Install it from the Roboflow plugin listing and sign in to Roboflow when asked.

To configure the server manually instead, add this to ~/.codex/config.toml:

Connecting MCP Gateways (Pre-Registered Credentials)

Most MCP clients (Cursor, Claude Desktop, VS Code, Claude Code) register automatically using Dynamic Client Registration. Some platforms require a pre-registered client_id and client_secret instead - for example, Azure AI Foundry agents, Microsoft Copilot Studio, and TrueFoundry AI Gateway.

To connect one of these platforms:

  1. Go to "Workspace Settings > Developer" in the Roboflow dashboard

  2. Click "Create OAuth App" and fill in a name, redirect URI (matching your gateway's callback URL), and allowed scopes

  3. Set "Token endpoint authentication" to match your gateway: client_secret_basic (HTTP Basic header, used by Azure and TrueFoundry) or client_secret_post (secret in the form body)

  4. Copy the Client ID and Client Secret (shown once)

  5. In your gateway's connector form, enter:

Field
Value

MCP Server URL

https://mcp.roboflow.com/mcp

Authorization URL

https://app.roboflow.com/oauth/authorize

Token URL

https://app.roboflow.com/oauth/token

Discovery (OAuth AS metadata)

https://app.roboflow.com/.well-known/oauth-authorization-server

Scopes

Space-separated list (ex: workspace:read project:read model:infer offline_access)

Include offline_access in your scope list if the gateway supports refresh tokens.

For the full scope catalog, see Available Scopes.

Tools

Most MCP clients namespace tool names, so projects_list appears as mcp__roboflow__projects_list. Each tool declares the OAuth scopes it needs, and your client only gets the scopes you approve at sign-in. For the current catalog, see the MCP tool list.

Agent

Hand a task to the Roboflow agent and collect what it produced.

Tool
Description

agent_chat

Chat with the Roboflow AI agent for Q&A, Workflow building, and solution planning.

agent_chat_result

Collect the result of an agent_chat run that was still working.

agent_conversations_list

List agent conversations in the workspace.

agent_conversation_get

Get one conversation with its message history.

agent_workflow_publish

Publish the latest agent-edited draft of a Workflow.

Projects

Create and inspect projects in your workspace.

Tool
Description

projects_list

List projects in the workspace.

projects_get

Get project detail including versions, classes, splits, and trained models.

projects_create

Create a new computer vision project.

projects_delete

Delete a project, moving it to the workspace Trash.

projects_fork

Enqueue an async fork of a public Universe project into your workspace.

projects_health

Get the dataset health check for a project.

datasets_rebalance_splits

Enqueue an async rebalance of a project's train, valid, and test splits.

Images

Upload images and find them again later.

Tool
Description

image_upload

Prepare a ZIP upload of images and optional annotation files.

image_upload_status

Check ZIP progress and report any images held for screening separately.

images_screening_status

Read the screening verdict for one held image ID.

images_search

Search for images inside a project.

images_workspace_search

Search images across the entire workspace using RoboQL.

images_update_metadata

Update metadata and tags on a single image.

images_batch_update_metadata

Batch-update metadata and tags on multiple images.

Annotation

Save labels and run automatic labeling.

Tool
Description

annotations_save

Save an annotation for an existing image.

autolabel_start

Start a hosted auto label job over a batch of images.

autolabel_job_get

Get per-subjob status and progress for an auto label job.

Batches

Group uploaded images before they enter labeling.

Tool
Description

annotation_batches_list

List upload batches in a project.

annotation_batches_get

Get details about one upload batch.

annotation_batches_create

Move selected images from one batch into a new batch.

annotation_batches_merge

Move all images from source batches into a target batch.

annotation_batches_delete

Delete a batch and move its images to unassigned.

annotation_batches_admin_list

List annotation board batches with cursor pagination.

annotation_batches_admin_get

Get details about one annotation board batch.

annotation_batches_admin_images_list

List image IDs in a batch with cursor pagination.

Annotation Jobs

Assign labeling work, run review, and accept results into the Dataset.

Tool
Description

annotation_jobs_list

List annotation jobs in a project.

annotation_jobs_get

Get details about one annotation job.

annotation_jobs_create

Create a job and move images from a batch into it.

annotation_jobs_update

Update a job's labeler, reviewer, or instructions.

annotation_jobs_images_list

List image IDs assigned to a job.

annotation_jobs_images_add

Move images into an existing job.

annotation_jobs_images_reassign

Create a job from selected images and clear their prior assignment.

annotation_jobs_submit_for_review

Advance a labeling job into review.

annotation_jobs_return_for_edits

Move a review job back to labeling, optionally with a new labeler.

annotation_jobs_review_image

Set the review status for one image in a job.

annotation_jobs_review_images

Set a status for every job image matching a current status.

annotation_jobs_accept_into_dataset

Finalize job images into the Dataset and assign splits.

annotation_jobs_move_to_unassigned

Remove a job and move its images to an unassigned batch.

annotation_jobs_delete_annotations

Delete the annotation data for every image assigned to a job.

Versions

Freeze a dataset version and export it.

Tool
Description

versions_generate

Create a version with optional preprocessing and augmentation.

versions_get

Get version info including splits and its trainings.

versions_export

Check or trigger a dataset export for a version.

versions_delete

Delete a version, moving it to the workspace Trash.

Models and Training

Train models, watch progress, and run inference.

Tool
Description

trainings_describe_recipe

Describe the tuning options for a model type and return a ready-to-submit recipe.

trainings_create

Start a training run on a dataset version.

trainings_list

List the training runs on a dataset version.

trainings_get

Get a training's status, produced models, and metrics.

trainings_stop

Request an early stop on an in-flight training run.

trainings_cancel

Cancel an in-flight training run.

trainings_delete

Delete a training run, moving it to the workspace Trash.

models_list

List trained models in a project.

models_get

Get details for a trained model.

models_infer

Run hosted inference on an image using a trained model.

models_upload_custom_weights

Get the recipe for uploading locally trained weights to Roboflow.

models_star_nas

Star or unstar a model found by neural architecture search.

Model Evaluations

Read mAP, confusion matrices, and per-class results.

Tool
Description

model_evals_list

List model evaluations in the workspace.

model_evals_get

Get the top-level summary for one evaluation.

model_evals_get_map_results

Get per-split mAP results.

model_evals_get_confidence_sweep

Get the precision, recall, and F1 confidence sweep.

model_evals_get_performance_by_class

Get per-class performance metrics for one split.

model_evals_get_confusion_matrix

Get the confusion matrix.

model_evals_get_image_predictions

Get per-image prediction stats, paginated.

model_evals_get_vector_analysis

Get clustering of image embeddings for the evaluation.

model_evals_get_recommendations

Get generated recommendations for the evaluation, if available.

Workflows

Build, validate, and run inference pipelines.

Tool
Description

workflows_list

List saved Workflows in the workspace.

workflows_get

Get details for a saved Workflow.

workflows_create

Create and save a new Workflow.

workflows_update

Update a saved Workflow's name and definition.

workflows_delete

Delete a saved Workflow, moving it to the workspace Trash.

workflows_run

Execute a saved Workflow on one or more images.

workflow_specs_validate

Validate a Workflow JSON definition without running it.

workflow_specs_run

Execute a Workflow from an inline JSON definition.

workflow_blocks_list

List all available Workflow blocks with a short summary of each.

workflow_blocks_get_schema

Get the full schema of one Workflow block.

For a gated Workflow, save a draft, run Eval checks if required, and wait for manual approval in the Roboflow app. Poll the gate verdicts and publish only when publishable is true. MCP cannot approve a Workflow version or a production device configuration proposal. See Save and Publish a Version.

Tool
Description

workflow_deploy_gates_openapi_get

Read the deploy gate API schemas.

workflow_deploy_gates_workspace_list

List Eval gates across the workspace.

workflow_deploy_gates_list

Read one Workflow's gates and statuses.

workflow_versions_save

Save a draft without publishing or starting checks.

workflow_version_deploy_gates_get

Read version verdicts and whether it can publish.

workflow_version_deploy_gates_run

Start Eval checks; poll for their verdicts.

workflow_version_deploy

Publish a version after every gate passes.

workflow_eval_deploy_gate_get

Read an Eval gate and its thresholds.

workflow_eval_deploy_gate_set

Set an Eval gate.

workflow_eval_deploy_gate_policy_update

Update its publishing policy.

workflow_eval_deploy_gate_new_check_thresholds_set

Set thresholds for new Eval Checks.

workflow_eval_deploy_gate_remove

Remove an Eval gate.

workflow_eval_deploy_checks_list

Read Eval deploy check results.

workflow_manual_approval_gate_get

Read manual approval rules.

workflow_manual_approval_gate_set

Set manual approval rules with a signed-in person's credential.

workflow_manual_approval_gate_remove

Remove manual approval rules with a signed-in person's credential.

workflow_version_approvals_list

List version approval records.

workflow_version_approval_get

Read approval status and eligible approvers.

Batch Processing

Run Workflows over local or cloud images and videos, or images already in your Asset Library. For local and cloud files, ask your MCP client for staging commands with batch_processing_guide. Run those commands in your terminal, then ask the client to start and monitor the job with batch_processing_run. For Asset Library images, use batch_processing_asset_library_job_create; the platform stages your selection.

Staging commands need inference-cli and a Roboflow API key on the machine running them. MCP's OAuth sign-in does not authenticate that CLI. Starting or restarting a job consumes credits. Download results before their staged batch expires, about 7 days after creation.

Tool
Description

batch_processing_guide

Get commands to stage files, run a Workflow, and download results.

batch_processing_staging_batches_list

List staged input and result batches in the Workspace.

batch_processing_staging_batch_get

Get a staged batch's file count and ingest progress.

batch_processing_run

Start or resume a staged job and return progress, result download URLs, or failure logs. Wait the number of seconds in retryAfterSeconds between calls and reuse the returned job ID.

batch_processing_staged_job_start

Start a fully ingested batch with custom timeouts or task limits. Reuse the same job_id and settings for retries.

batch_processing_asset_library_job_create

Create a job from exactly one selection: image_ids, a structured RoboQL query, or all_images=true. Reuse the same idempotency_key when retrying the same request.

batch_processing_asset_library_task_get

Track an Asset Library job's asynchronous task using the returned taskId.

batch_processing_jobs_list

Find jobs in the Workspace, with optional search and pagination.

batch_processing_job_get

Get a job's status, stage progress, and output batches using its jobId.

batch_processing_job_logs

Read paginated processing logs.

batch_processing_job_abort

Stop a running job. Partial results remain available.

batch_processing_job_restart

Restart a failed or aborted job, with optional compute changes.

batch_processing_staging_batch_files_list

List input or result files with signed download URLs.

Project Deployment

Manage a project's stable live endpoint and Active Learning.

Tool
Description

project_deployment_get

Get the live endpoint state for a project.

project_deployment_launch

Create or prepare a Project Deployment.

project_deployment_set_model

Change the default model behind a deployment without changing its endpoint.

project_deployment_run

Run inference through the project's live endpoint.

project_deployment_enable_active_learning

Enable Active Learning for a deployment.

project_deployment_disable_active_learning

Pause Active Learning collection.

project_deployment_configure_active_learning

Configure how a deployment collects Active Learning data.

project_deployment_list_review_queues

List review queues fed by production inference.

Vision Events

Query production events and manage use cases.

Tool
Description

vision_events_query

Query events by ID or grouped filters with pagination.

vision_events_use_cases_list

List the vision event use cases in the workspace.

vision_events_custom_metadata_schema_get

Get the custom metadata schema discovered for a use case.

vision_events_use_case_create

Create a new use case.

vision_events_use_case_rename

Rename an existing use case.

vision_events_use_case_archive

Archive a use case.

vision_events_use_case_unarchive

Restore a previously archived use case.

vision_events_delete

Delete selected events, with optional cleanup of unused media.

Devices and Streams

Monitor, configure, and control edge devices managed by Deployment Manager. The devices_streams_* tools below work with streams on those devices, not Cloud Streaming sources or jobs. Do not substitute them for the Cloud Streaming interfaces.

Commands such as restart, pause, and power-cycle are queued for the device, which picks them up on its next poll. A success means the command was queued, not that it ran. A command expires if the device does not pick it up within 5 minutes, so ask your agent to check the device afterward.

Monitor Devices

Tool
Description

devices_list

List the devices in your workspace.

devices_get

Get one device's details and status.

devices_get_snapshot

Get a device's full current state in one call.

devices_get_logs

Read device logs.

devices_get_telemetry

Get hardware metrics (CPU, memory, disk, GPU) and stream FPS.

devices_get_events

List device and stream events, such as boots, errors, and config changes.

devices_list_events

List events across every device in the workspace.

devices_get_deployments

Get a device's deployment history and what happened during each one.

devices_get_exception_occurrences

List each time one error happened on a device.

devices_get_services

List the services a device runs and their status.

devices_get_service_series

Chart one service metric over time.

devices_get_plc_status

Check whether a device's PLC Relay is connected to its PLCs.

devices_get_event_store_stats

Check a device's Event Store usage against its limits.

devices_get_inference_versions

See which inference version each device runs.

devices_get_secure_gateway_status

Check a device's Secure Gateway setup and cache status.

Configure Devices

Tool
Description

devices_get_config

Get a device's configuration.

devices_update_config

Propose a configuration change. Production approval and maintenance windows can delay application.

devices_set_service_version

Set the inference or manager version on a device.

devices_apply_pending_config

Apply changes waiting for the next maintenance window now.

devices_get_config_history

List a device's past configurations, newest first.

devices_get_default_config

Get the configuration new devices in your workspace start from.

devices_update_default_config

Change the configuration new devices start from.

Streams and Cameras

Tool
Description

devices_streams_list

List the streams on a device.

devices_streams_get

Get one stream's status and settings.

devices_streams_create

Add a camera stream that runs a Workflow.

devices_streams_update

Change a stream's settings.

devices_streams_pause

Pause a stream without removing it.

devices_streams_resume

Resume a paused stream.

devices_streams_trigger

Run the Workflow once on a Triggered stream.

devices_streams_terminate

Remove a stream from a device for good.

devices_streams_sample_frame

See what a camera sees right now, and get the frame as an image URL for Workflows.

devices_streams_capture_frame

Capture a frame for training; report when it is held for upload screening.

devices_discover_cameras

Scan a device's network for cameras.

devices_restart_poe_port

Power-cycle the PoE port of a stuck camera.

devices_get_stream_options

List the streams on every device in the workspace.

Manage Devices

Tool
Description

devices_create

Add a device, including a Secure Gateway with runtime docker.

devices_update

Rename a device or set its environment variables.

devices_restart_inference

Restart a device's inference server.

devices_redeploy

Get a new install command to reinstall Deployment Manager on a device.

devices_send_command

Queue a device command, including an asynchronous network probe.

devices_snooze_alerts

Snooze a device's health alerts for one day.

devices_delete

Delete a device. This cannot be undone.

Device Groups

Tool
Description

device_groups_list

List your device groups.

device_groups_get

Get one device group.

device_groups_create

Create a device group.

device_groups_update

Rename a group or replace its members.

device_groups_add_devices

Add devices to a group.

device_groups_remove_devices

Remove devices from a group.

device_groups_delete

Delete a group. Its devices are kept.

Cloud Storage

Mirror an S3 or GCS bucket into a project for labeling or training. To process files without importing them, use Batch Processing.

Tool
Description

connect_cloud_storage

Set up a bucket mirror end to end, from credential to first run.

credentials_list

List cloud storage credentials in the workspace.

credentials_create

Create a cloud storage credential.

credentials_delete

Delete a credential.

datasources_list

List bucket mirror configurations in the workspace.

datasource_get

Get full detail for a single datasource.

datasource_create

Create a datasource that mirrors a bucket path into a project.

datasource_update

Update a datasource. Only the fields you pass change.

datasource_delete

Delete a datasource. Already mirrored images stay in the project.

datasource_validate

Check that Roboflow can reach the datasource's bucket.

datasource_trigger

Start a mirror run.

datasource_job_get

Get the status and statistics of one mirror run.

Universe

Search public datasets and models on Roboflow Universe.

Tool
Description

universe_search

Search Roboflow Universe for datasets or models.

universe_dataset_images_search

Search images inside a public Universe dataset given its URL.

Media

Look at an image or video before deciding what to build.

Tool
Description

media_upload

Prepare a local image or video for analysis.

media_upload_finalize

Validate a staged upload and publish it.

media_analyze

Analyze an image or short video with a vision model to understand its contents.

media_trim

Cut a clip from an Asset Library video and get an analyzable public URL.

API Keys

Create and retire keys for your workspace.

Tool
Description

api_keys_list

List all API keys for the workspace.

api_keys_get

Get metadata for a single key.

api_keys_get_publishable

Get the workspace's publishable key.

api_keys_create

Create a new API key.

api_keys_update

Update a key's name, scopes, metadata or rotation schedule.

api_keys_protect

Mark a key as protected so it cannot be revoked or disabled.

api_keys_disable

Disable or re-enable a key without revoking it.

api_keys_revoke

Permanently revoke a key.

api_keys_roll

Revoke a key and create its replacement in one step. Returns the new secret once.

api_keys_owner_candidates

List the members who can roll a key and be its rotation owners.

Trash

Restore something that was deleted.

Tool
Description

trash_list

List soft-deleted items currently in the workspace Trash.

trash_restore_project

Restore a deleted project.

trash_restore_version

Restore a deleted dataset version.

trash_restore_workflow

Restore a deleted Workflow.

trash_restore_training

Restore a deleted training run.

Other

Poll long-running work and send feedback.

Tool
Description

async_tasks_get

Poll an async task by id, such as a project fork or a split rebalance.

meta_feedback_send

Report a bug, missing feature, or documentation issue to the Roboflow team.

Last updated

Was this helpful?