Categories › Data & Databases › Vector databases & embeddings
Hosted EEG embeddings API: any montage and sampling rate, EDF/BDF/FIF/NPY, 768-d vector per window
Remote server: your requests and data go to api.neuroencoder.com. Claude Code: claude mcp add --transport http neuroencoder-eeg-embeddings https://api.neuroencoder.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
account — This API key: tier, limits and usage this month.list_samples — Precomputed real outputs (no upload needed): ids, titles, sizes, download URLs.get_sample — One sample: README, licence, channels_used, and its embeddings in the POST /v1/embeddings response format (first windows only for long ones)create_upload — Start an upload of a local .edf, .bdf or .npy file (at most 2 GB). Returns id and a presigned upload_url: PUT the file there within 10 minutstart_embedding_job — Queue an embeddings job on an uploaded file. window_seconds: 2 to 30 (default 30); stride_seconds: default window_seconds. picks: EDF/BDF chstart_sleep_staging_job — Queue sleep staging of an uploaded whole-night PSG (.edf/.bdf; >= 1 EEG channel with a 10-20 label at >= 100 Hz; EOG used if present). eeg_cget_job — A job's status (queued, running, succeeded, failed, cancelled, expired), usage, error or result. Poll every 5 s while queued or running.get_result_url — Fresh presigned GET URLs (10 minutes) of a succeeded job's result. Embeddings: .npy float32 [windows, 768], window i starts at i * t_start_sNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.