Roboflow
Create computer vision projects, train models, and deploy them with Roboflow MCP server
Documentation
Install
One server. Every agent.
One hosted MCP server. Drop it into the agent of your choice.
Any agentClaudeClaude CodeCursorChatGPTCodexGemini CLI
Fetch https://docs.roboflow.com/agents/setup.md and follow the steps to install the connection to Roboflow MCP server Copy
Paste it into your coding agent and it walks you through the rest. Setting up by hand? The server is https://mcp.roboflow.com/mcp.
Open the Roboflow listing, select Connect, then sign in to Roboflow. Available on desktop, web and mobile.
claude plugin marketplace add roboflow/computer-vision-skills Copy claude plugin install roboflow Copy
Run these commands in your terminal, then sign in to Roboflow. Claude Code CLI has no documented browser install link.
Opens the Roboflow plugin listing. Sign in if prompted and confirm the install on Cursor to add MCP and skills.
Opens the Roboflow plugin listing. Install the plugin and sign in to Roboflow when prompted to connect your account.
codex plugin marketplace add roboflow/computer-vision-skills Copy
Open Plugins in Codex, choose the Roboflow source, and install the Roboflow plugin.
npx skills add roboflow/computer-vision-skills -a gemini-cli Copy gemini mcp add --scope project --transport http roboflow https://mcp.roboflow.com/mcp Copy
Then run /mcp auth roboflow in Gemini CLI to sign in. Gemini CLI has no documented browser install link.
281 tools for every step, from dataset to deployment.
Once connected, your agent calls these directly. Each tool maps to something you’d otherwise do in the dashboard or the API. The tool reference lists every one.
| Category | What your agent can do | Tools |
|---|---|---|
| Agent | chat with the Roboflow AI agent for Roboflow Q&A, advanced Workflow building, and CV solution planning - agent_chat - agent_chat_result - agent_conversations_list - agent_conversation_get - agent_workflow_publish | 5 |
| Projects | manage projects in your workspace - projects_list - projects_create - projects_health - projects_get - projects_delete - projects_fork - datasets_rebalance_splits | 7 |
| Project Deployment | launch and manage a stable live endpoint for a project - project_deployment_get - project_deployment_launch - project_deployment_set_model - project_deployment_run - project_deployment_enable_active_learning - project_deployment_disable_active_learning - project_deployment_configure_active_learning - project_deployment_list_review_queues | 8 |
| Images | upload images and videos, search, and manage images across projects - image_upload - image_upload_files - image_upload_status - images_add_to_project - video_upload - video_upload_status - images_update_metadata - images_batch_update_metadata - images_workspace_search - images_search - universe_dataset_images_search | 11 |
| Media Understanding | analyze images and short videos with a vision model to scope CV tasks, suggest classes, and plan workflows - media_analyze - media_upload - media_trim - media_upload_finalize | 4 |
| Annotations | save image annotations and Action Recognition video segments - video_segments_annotate - annotations_save | 2 |
| Auto-label | kick off and track hosted auto-labeling jobs - autolabel_models_list - autolabel_preview - autolabel_start - autolabel_job_get | 4 |
| Annotation Administration | explicitly manage annotation batches, assignments, review, and Dataset acceptance - annotation_board_status - annotation_batches_list - annotation_batches_get - annotation_batches_admin_list - annotation_batches_admin_get - annotation_batches_admin_images_list - annotation_batches_create - annotation_batches_merge - annotation_batches_delete - annotation_jobs_list - annotation_jobs_get - annotation_jobs_images_list - annotation_jobs_create - annotation_jobs_images_reassign - annotation_jobs_images_add - annotation_jobs_update - annotation_jobs_submit_for_review - annotation_jobs_return_for_edits - annotation_jobs_review_image - annotation_jobs_review_images - annotation_jobs_accept_into_dataset - annotation_jobs_move_to_unassigned - annotation_jobs_delete_annotations | 23 |
| Versions | create and inspect dataset versions - versions_generate - versions_get - versions_delete - versions_export | 4 |
| Models | train models and monitor training progress - models_list - models_get - models_infer - trainings_describe_recipe - trainings_create - models_custom_weights_upload_guide - trainings_list - trainings_get - trainings_cancel - trainings_stop - trainings_delete - models_star_nas | 12 |
| Model Evaluations | inspect held-out evaluation results for trained models — mAP, precision/recall sweeps, per-class breakdowns, confusion matrices, vector clustering, per-image predictions, and accuracy/latency comparisons - model_evals_compare - model_evals_list - model_evals_get - model_evals_get_map_results - model_evals_get_confidence_sweep - model_evals_get_performance_by_class - model_evals_get_confusion_matrix - model_evals_get_vector_analysis - model_evals_get_image_predictions - model_evals_get_recommendations | 10 |
| Workflows | build and execute inference pipelines - workflows_list - workflows_get - workflows_create - workflows_update - workflows_delete - workflow_blocks_list - workflow_blocks_get_schema - workflow_specs_validate - workflows_run - workflow_specs_run | 10 |
| Workflow Evals | design evaluations for Workflows: discover evaluators and schemas, author Specs and Eval Datasets, manage Cases, and confirm Workflow output bindings - workflow_evals_capabilities - workflow_evals_evaluators_list - workflow_evals_evaluators_get - workflow_evals_schema_get - workflow_evals_openapi_get - workflow_evals_agent_manifest - workflow_evals_agent_resources_list - workflow_evals_agent_resource_get - workflow_evals_operation_get - workflow_evals_list - workflow_evals_create - workflow_evals_get - workflow_evals_update - workflow_evals_delete - workflow_evals_specs_list - workflow_evals_specs_create - workflow_evals_specs_get - workflow_evals_specs_update - workflow_evals_specs_validate - workflow_evals_specs_compatible_datasets - workflow_evals_datasets_list - workflow_evals_datasets_create - workflow_evals_datasets_get - workflow_evals_datasets_update - workflow_evals_datasets_update_contract - workflow_evals_datasets_compatible_specs - workflow_evals_cases_list - workflow_evals_cases_create - workflow_evals_cases_get - workflow_evals_cases_replace - workflow_evals_cases_delete - workflow_evals_cases_import - workflow_evals_case_imports_get - workflow_evals_case_assets_upload - workflow_evals_case_assets_upload_complete - workflow_evals_bindings_suggest - workflow_evals_bindings_validate | 37 |
| Workflow Eval Runs | run Workflow Evals against one or more Workflows, prepare candidate outputs, inspect and compare per-Case results, export them, and analyze image embeddings - workflow_evals_case_preparations_start - workflow_evals_case_preparations_get - workflow_evals_case_preparations_resume - workflow_evals_case_preparations_cases - workflow_evals_runs_list - workflow_evals_runs_start - workflow_evals_runs_get - workflow_evals_runs_configuration - workflow_evals_runs_cancel - workflow_evals_runs_retry_failed - workflow_evals_runs_replay - workflow_evals_runs_rescore - workflow_evals_runs_delete - workflow_evals_executions_list - workflow_evals_executions_get - workflow_evals_executions_configuration - workflow_evals_executions_input_cases - workflow_evals_executions_submit_capture - workflow_evals_results_overview - workflow_evals_results_cases_list - workflow_evals_results_case_get - workflow_evals_results_compare - workflow_evals_exports_start - workflow_evals_exports_get_job - workflow_evals_exports_download_url - workflow_evals_embeddings_start - workflow_evals_embeddings_get - workflow_evals_embeddings_cancel | 28 |
| Batch Processing | run Workflows over huge image/video sets: Asset Library selections (platform-staged) or batches you stage yourself - batch_processing_asset_library_job_create - batch_processing_asset_library_task_get - batch_processing_guide - batch_processing_staging_batches_list - batch_processing_staging_batch_get - batch_processing_staging_batch_files_list - batch_processing_jobs_list - batch_processing_job_get - batch_processing_staged_job_start - batch_processing_job_abort - batch_processing_job_restart - batch_processing_job_logs - batch_processing_run | 13 |
| Devices | inspect, provision, configure, and control Roboflow Deployment Manager devices via the external Deployments v2 API - devices_list - devices_create - devices_get - devices_get_config - devices_get_default_config - devices_update_config - devices_set_service_version - devices_get_config_history - devices_restart_inference - devices_discover_cameras - devices_streams_pause - devices_streams_resume - devices_streams_trigger - devices_restart_poe_port - devices_streams_create - devices_streams_terminate - devices_get_secure_gateway_status - devices_streams_list - devices_streams_get - devices_get_logs - devices_get_telemetry - devices_get_deployments - devices_get_exception_occurrences - devices_get_snapshot - devices_get_events - devices_get_services - devices_get_plc_status - devices_get_event_store_stats - devices_get_service_series - devices_update - devices_delete - devices_send_command - devices_redeploy - devices_provisioning_qr - devices_os_image_create - devices_os_image_get - devices_apply_pending_config - devices_update_default_config - devices_streams_update - devices_streams_delete - devices_streams_capture_frame - devices_streams_sample_frame - devices_snooze_alerts - devices_list_events - devices_get_inference_versions - devices_get_stream_options - device_groups_list - device_groups_get - device_groups_create - device_groups_update - device_groups_add_devices - device_groups_remove_devices - device_groups_delete - device_groups_get_config - device_groups_update_config | 55 |
| API Keys | manage workspace API keys - api_keys_list - api_keys_get - api_keys_owner_candidates - api_keys_get_publishable - api_keys_create - api_keys_update - api_keys_protect - api_keys_disable - api_keys_revoke - api_keys_roll | 10 |
| Folders | list the workspace folders visible to the credential - folders_list | 1 |
| Workspace Announcements | schedule the banner announcements shown to everyone in the workspace - workspace_announcements_list - workspace_announcements_create - workspace_announcements_update - workspace_announcements_delete | 4 |
| Vision Events | query and report on production vision events (quality checks, inventory counts, safety alerts, operator feedback) and manage the use cases they are grouped under and the filters saved for them - vision_events_query - vision_events_use_cases_list - vision_events_custom_metadata_schema_get - vision_events_image_metadata_schema_get - vision_events_use_case_create - vision_events_use_case_rename - vision_events_use_case_archive - vision_events_use_case_unarchive - vision_events_saved_filters_list - vision_events_saved_filter_get - vision_events_saved_filter_create - vision_events_saved_filter_update - vision_events_saved_filter_delete | 13 |
| Universe | search public datasets on Roboflow Universe - universe_search | 1 |
| Datasources | configure and run cloud-bucket mirroring into projects - datasources_list - datasource_get - datasource_validate - datasource_job_get - datasource_create - datasource_update - datasource_delete - datasource_trigger - connect_cloud_storage | 9 |
| Credentials | manage cloud-storage credentials used by datasources - credentials_list - credentials_delete - get_aws_storage_credential_setup_link | 3 |
| Trash | list and restore soft-deleted items - trash_list - trash_restore_project - trash_restore_version - trash_restore_workflow - trash_restore_training | 5 |
| Async tasks | poll the status of long-running async operations - async_tasks_get | 1 |
| Meta | report issues or suggestions - meta_feedback_send | 1 |
12 Skills, exposed to your agent.
Skills are markdown playbooks your agent reads as MCP resources. Connected clients pick the right one for the task at hand.
- 01
draw-vision
Draw computer vision annotations, labels, and predictions over images and videos using supervision-js in JavaScript/TypeScript or Supervision in Python. - 02
api-reference
Protocol-level facts for Roboflow REST and Inference APIs — URL patterns, auth, parameters, error codes, and SDK quick-start. For deployment strategy and Workflow execution patterns, see roboflow-inference. - 03
batch-processing
Use when running a Roboflow Workflow over many images or videos with batch processing — Asset Library jobs (the platform stages workspace images for you) or staged jobs (you stage external local/cloud files with the inference-cli), plus monitoring jobs, downloading results, and routing imports to datasources (bucket mirror) instead. - 04
cloud-storage
Use when connecting cloud storage (AWS S3 / S3-compatible or Google Cloud Storage) to Roboflow to mirror images into a workspace — creating storage credentials, defining datasources (bucket-mirror configs), selecting objects with glob rules, validating access, and running/scheduling mirror jobs. - 05
custom-weights-upload
Use when uploading locally trained model weights (YOLO, RF-DETR, YOLO-NAS, PaliGemma, Florence-2) to Roboflow — the client-side Python SDK upload flow, safe API key handling, per-family packaging requirements, and verifying the upload. - 06
data-management
Use when uploading images, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification), tags, splits, versions, or RoboQL search. - 07
inference
Deployment option comparison (serverless, dedicated, self-hosted, batch) and Workflow execution patterns. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference. - 08
plans-and-pricing
Use when answering questions about Roboflow plans, credit usage, or cost estimation; directs users to roboflow.com/pricing for current dollar amounts. - 09
product-navigation
Use when explaining where Roboflow features live in the app.roboflow.com web app, mapping intents like upload, annotate, train, deploy to specific page URLs. - 10
training-and-evaluation
Use when training Roboflow models, diagnosing why a model underperforms, improving accuracy, or setting up a production feedback loop — covers architecture selection, model IDs, checkpoints, Model Evaluation (confusion matrix, per-class metrics, MCP eval tools), the diagnosis-first improvement playbook, and Active Learning through the Project Model Workflow block. - 11
universe
Use when searching for or using public datasets/models on Roboflow Universe (universe.roboflow.com), the open repository of 1M+ computer vision datasets and 50K+ pre-trained models. - 12
workflow-from-eval
Build or improve a Roboflow Workflow using eval-driven search. Prefer this for open-ended business problems where the approach is unclear, or when comparing alternatives. A business goal plus images or video is enough to start; no existing Workflow or Eval is required. Build an example suite and scorecard the user approves, compare candidate Workflows, then tune and validate the winner. Use direct tools for straightforward builds and edits, Workflow Evals tools for measuring one existing Workflow once, and training skills for training a model.
Skills
Skills load when your agent needs them. No setup on your end.
Once your agent is connected to mcp.roboflow.com, it can list and read every Skill alongside the tools. Want them as local files instead? Install the bundle.
npx skills add roboflow/computer-vision-skills Copy
llms.txt
A short, LLM-friendly summary lives at /llms.txt
Quick answers about the server, Skills, auth, and how MCP fits into the rest of Roboflow.
curl https://mcp.roboflow.com/llms.txt Copy