Endpoints: 76,849MCP servers: 32,730Payout addresses: 3,825Paid calls: 6,166Letters: 84Defects: 3,898counted 1 min ago
teppi

Server definition

Hash
sha256:0461369871088e1506b62abe27289b53e538f5a23839e152ef2cd0c446f28739
What it is
What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{ "instructions": "EEG embeddings from EPI-300K: one 768-d vector per window (30 s by default, window_seconds 2 to 30). Without data: list_samples, get_sample. With a local .edf/.bdf/.npy file: create_upload, PUT the file to upload_url yourself, start_embedding_job, get_job until succeeded, then get_result_url (.npy float32 [windows, 768]). Sleep staging of a whole-night PSG: create_upload, PUT, start_sleep_staging_job, get_job, get_result_url (hypnogram JSON and CSV). A job with data_use \"contribute\" keeps a de-identified copy of the signal that may train our models; without data_use, or with \"zero_retention\", no copy is kept after the job (its upload is deleted when it ends, its result after 7 days): https://docs.neuroencoder.com/data-use. Research use only; not a medical device.", "tools": [ { "description": "This API key: tier, limits and usage this month.", "inputSchema": { "properties": {}, "title": "accountArguments", "type": "object" }, "name": "account", "outputSchema": null }, { "description": "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 minutes with exactly upload_headers (e.g. curl -X PUT --upload-file night.edf -H 'Content-Length: N' '<upload_url>', no Authorization header), then call start_embedding_job with the id. Only the extension of filename is used.", "inputSchema": { "properties": { "bytes": { "title": "Bytes", "type": "integer" }, "filename": { "title": "Filename", "type": "string" } }, "required": [ "filename", "bytes" ], "title": "create_uploadArguments", "type": "object" }, "name": "create_upload", "outputSchema": null }, { "description": "A job's status (queued, running, succeeded, failed, cancelled, expired), usage, error or result. Poll every 5 s while queued or running.", "inputSchema": { "properties": { "job_id": { "title": "Job Id", "type": "string" } }, "required": [ "job_id" ], "title": "get_jobArguments", "type": "object" }, "name": "get_job", "outputSchema": null }, { "description": "Fresh presigned GET URLs (10 minutes) of a succeeded job's result. Embeddings: .npy float32 [windows, 768], window i starts at i * t_start_step s. Sleep staging: url = hypnogram JSON (stage, probabilities, confidence per 30 s epoch), csv_url = CSV, plus the summary.", "inputSchema": { "properties": { "job_id": { "title": "Job Id", "type": "string" } }, "required": [ "job_id" ], "title": "get_result_urlArguments", "type": "object" }, "name": "get_result_url", "outputSchema": null }, { "description": "One sample: README, licence, channels_used, and its embeddings in the POST /v1/embeddings response format (first windows only for long ones).", "inputSchema": { "properties": { "name": { "title": "Name", "type": "string" } }, "required": [ "name" ], "title": "get_sampleArguments", "type": "object" }, "name": "get_sample", "outputSchema": null }, { "description": "Precomputed real outputs (no upload needed): ids, titles, sizes, download URLs.", "inputSchema": { "properties": {}, "title": "list_samplesArguments", "type": "object" }, "name": "list_samples", "outputSchema": null }, { "description": "Queue an embeddings job on an uploaded file. window_seconds: 2 to 30 (default 30); stride_seconds: default window_seconds. picks: EDF/BDF channel labels to keep; channel_names: 10-20 labels overriding the file's; sfreq: required for .npy. Bills 30 s of EEG per window at any window_seconds (refunded on failure). Poll get_job.", "inputSchema": { "properties": { "channel_names": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "title": "Channel Names" }, "file_id": { "title": "File Id", "type": "string" }, "picks": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "title": "Picks" }, "sfreq": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Sfreq" }, "stride_seconds": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null, "title": "Stride Seconds" }, "window_seconds": { "default": 30, "title": "Window Seconds", "type": "number" } }, "required": [ "file_id" ], "title": "start_embedding_jobArguments", "type": "object" }, "name": "start_embedding_job", "outputSchema": null }, { "description": "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_channel/eog_channel: channels for the YASA features; picks, channel_names as for embeddings. Counts 1 night of the weekly quota (refunded on failure). Poll get_job, then get_result_url. Research use only, not a medical device.", "inputSchema": { "properties": { "channel_names": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "title": "Channel Names" }, "eeg_channel": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Eeg Channel" }, "eog_channel": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Eog Channel" }, "file_id": { "title": "File Id", "type": "string" }, "picks": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null, "title": "Picks" }, "units": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "title": "Units" } }, "required": [ "file_id" ], "title": "start_sleep_staging_jobArguments", "type": "object" }, "name": "start_sleep_staging_job", "outputSchema": null } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:0461369871088e1506b62abe27289b53e538f5a23839e152ef2cd0c446f28739 | sha256sum