{"name":"com.mozilladatacollective/datasets","slug":"mozilladatacollective-datasets","title":"Mozilla Data Collective","description":"Search the Mozilla Data Collective catalog of ethically sourced AI training datasets.","url":"https://mcp.market/server/mozilladatacollective-datasets","rating":null,"grade":"C","score":69,"certified":false,"status":"active","category":"search","tags":["search"],"presence":{"score":8,"stars":null,"forks":null,"downloads_week":null,"last_push_at":null,"license":null},"uptime":{"percent":100,"checks":9,"ok":9,"last_checked_at":"2026-09-21T13:55:55.032Z","last_ok_at":"2026-09-21T13:55:55.032Z","latency_ms":101},"claimed":false,"transport":"remote","callable_via_gateway":true,"default_price_micros":0,"repository":null,"website":"https://mozilladatacollective.com","version":"0.1.0","remotes":[{"type":"streamable-http","url":"https://mozilladatacollective.com/api/mcp"}],"packages":[],"tools":[{"name":"fetch","description":"Fetch the full public details of one Mozilla Data Collective dataset by id or slug: description, organization, task, locale, license, format, size, pricing, and its page URL.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"id":{"type":"string","minLength":1,"maxLength":500,"description":"Dataset id or slug, as returned in the id field of search results."}},"required":["id"],"$schema":"https://json-schema.org/draft/2020-12/schema"}},{"name":"list_filters","description":"List every value the search tool's filters accept: the tasks, locales, licenses and formats present in the catalog, plus the sort and date-range options. Task and license values are abbreviations, so taskLabels and licenseLabels spell them out. Filter values are matched exactly, so call this before filtering a search rather than guessing values. Takes no arguments.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{},"$schema":"https://json-schema.org/draft/2020-12/schema"}},{"name":"search","description":"Search the Mozilla Data Collective catalog of AI training datasets by natural-language query, optionally narrowed by task, language, license, format, price, sample availability or publish date. Returns matching datasets as {id, title, url}; pass an id to the fetch tool for full details. Call list_filters first if you intend to filter — filter values must match the catalog exactly.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"query":{"type":"string","minLength":1,"maxLength":500,"description":"Natural-language search query describing the datasets you are looking for, e.g. 'Spanish speech recordings for TTS training'. Descriptive phrases retrieve better than single keywords."},"limit":{"default":10,"description":"Maximum number of results to return (1-25).","type":"integer","minimum":1,"maximum":25},"task":{"description":"Restrict to these machine-learning tasks, e.g. ['ASR', 'TTS'].","minItems":1,"maxItems":20,"type":"array","items":{"type":"string","enum":["N/A","NLP","ASR","LID","TTS","MT","LM","LLM","NLU","NLG","CALL","RAG","CV","ML","OTH"]}},"locale":{"description":"Restrict to these language/locale codes, e.g. ['sw', 'pt-BR']. Values must match exactly (case-sensitive); call the list_filters tool to get the valid ones.","minItems":1,"maxItems":20,"type":"array","items":{"type":"string","minLength":1}},"license":{"description":"Restrict to these license abbreviations, e.g. ['CC0-1.0', 'CC-BY-4.0']. Values must match exactly (case-sensitive); call the list_filters tool to get the valid ones.","minItems":1,"maxItems":20,"type":"array","items":{"type":"string","minLength":1}},"format":{"description":"Restrict to these file formats, e.g. ['WAV', 'MP3']. Values must match exactly (case-sensitive); call the list_filters tool to get the valid ones.","minItems":1,"maxItems":20,"type":"array","items":{"type":"string","minLength":1}},"isPaid":{"description":"true returns only paid datasets, false only free ones. Omit to include both.","type":"boolean"},"hasSample":{"description":"true returns only datasets that publish a downloadable sample, useful when the user wants to try data before committing. false behaves the same as omitting it.","type":"boolean"},"sort":{"description":"Result ordering. Defaults to 'relevance'; use 'newest' or 'size' only when the user asks for it.","type":"string","enum":["relevance","newest","size"]},"sortDirection":{"description":"Direction for the sort field. Only meaningful alongside sort='newest' or sort='size'.","type":"string","enum":["asc","desc"]},"uploadDate":{"description":"Restrict to datasets published within this recent window.","type":"string","enum":["today","thisWeek","thisMonth","thisYear"]}},"required":["query"],"$schema":"https://json-schema.org/draft/2020-12/schema"}}],"scan":{"score":69,"grade":"C","scanned_at":"2026-09-20T00:27:54.315Z","report":{"scannerVersion":"0.1.9","scannedAt":"2026-09-20T00:27:54.292Z","components":{"code":{"score":-1,"max":25,"notes":["remote-only server, no package to scan"]},"reliability":{"score":20,"max":20,"notes":["remote reachable in 1729ms"]},"poisoning":{"score":15,"max":15,"notes":["3 tool descriptions checked"]},"auth":{"score":10,"max":15,"notes":["open endpoint, read-only tools"]},"maintenance":{"score":3,"max":15,"notes":["no repository listed"]},"identity":{"score":4,"max":10,"notes":["verified namespace with website, no repo"]}},"findings":[{"id":"maint.no-repo","severity":"low","component":"maintenance","title":"No source repository listed"}],"inputs":{"probes":[{"url":"https://mozilladatacollective.com/api/mcp","reachable":true,"authRequired":false,"latencyMs":1729,"serverInfo":{"name":"mozilla-data-collective","version":"0.1.0"}}],"packages":[],"repo":{"found":false},"icon":{"url":null,"source":"none"},"presence":{"stars":null,"forks":null,"downloadsWeek":null,"license":null,"lastPushAt":null,"score":8}}}},"grade_history":[],"reviews":[]}