$ loading_
Control and manage FiftyOne datasets through AI assistants via MCP.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "FiftyOne MCP Server" yet — see the docs or source repo.
Using the FiftyOne MCP Server, list the available datasets and summarize each dataset's sample count, label types, and most recent update time.
A dataset list with a concise summary of key statistics for each dataset.
Using the FiftyOne MCP Server, filter samples in a specified dataset whose detection confidence is below 0.3, and count them by class.
A filtered sample set plus aggregated counts grouped by class.
Using the FiftyOne MCP Server, create a view for this dataset that includes only nighttime scenes and pedestrian labels, and save it as "night_pedestrian_review".
A reusable saved dataset view for later review and analysis.
Connect to the mcp API via MCP to extend AI tool capabilities.
Build, debug, and manage software tasks with natural language across LLMs.
Use natural language to query ftrack projects, tasks, and production statuses.
Access multiple AI providers in one terminal for generation, search, and comparison.
Call tools like weather lookup via MCP with reusable resources and prompts.
Manage Redmine projects, issues, time logs, wiki, and files via MCP.