Nimbus BCI is an MCP server with 63 tools an agent can call, among them account.whoami, bids.export_dataset, bids.export_execution. It answers at https://nimbus-mcp.fly.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 5 October 2026; the last check, on 21 November 2026, succeeded.
BCI/EEG toolkit: public MOABB/BNCI datasets, pipeline build/validate, hosted training, BIDS export.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
account.whoami | Who you are authenticated as: account email, plan (isPro / pioneer), this month's free-run quota, and — with a hosted token — the token name and days until it expires. Call this first when setup guidance appears or to check which credential |
bids.export_dataset | Export a Nimbus dataset as a BIDS-layout zip (local: saved to NIMBUS_EXPORT_DIR/bids/; hosted gateway: inline ``contentBase64``, up to 1 MB). Continuous sources (EDF/BDF uploads, stream recordings) export as BIDS-raw (EDF byte-passthrough; Inputs: dataset, subjects, kind |
bids.export_execution | Export an execution's results as a BIDS-derivative zip (metrics.json, per-subject participants.tsv, protocol.json, full pipeline_snapshot.json, predictions.tsv when stored, provenance/execution.json). Local: saved to NIMBUS_EXPORT_DIR/bids/ Inputs: execution_id |
calibration.pause | Pause a running calibration between trials (cues hold; resume anytime). Inputs: execution_id |
calibration.resume | Resume a paused calibration session. Inputs: execution_id |
calibration.start | Start a guided subject calibration session (NON-BLOCKING; confirm-gated — the device goes on a human's head). The Nimbus Studio app shows the cues on its calibration dashboard automatically; poll calibration.status. Requires a Pro plan (hos Inputs: paradigm, confirm, trials_per_class, classes, name, device_type |
calibration.status | Live snapshot of a calibration session (phase, current trial, progress, paused). Once complete, carries the recorded upload — call calibration.train to turn it into the subject's own classifier. Inputs: execution_id |
calibration.train | Train the subject's own classifier from a COMPLETED calibration session (NON-BLOCKING). Fetches the recorded upload, wires it into a train pipeline as a custom_data source, and starts the run. Requires a Pro plan (custom_data training is fr Inputs: execution_id, paradigm, template_id, train_graph, name |
catalog.datasets | Curated public EEG datasets (MOABB packs) available to pipelines. Inputs: only_on_disk |
catalog.leaderboard | Public benchmark leaderboard: pipeline rankings per dataset. Two tracks: the top-level ``within_session`` block (curated suite pipelines) and ``crossSubject`` (leave-one-subject-out — curated pipelines plus BYO ``python_model`` submissions; Inputs: dataset_id |
catalog.node_schema | Full config JSON schema + input/output ports for one node type. Inputs: node_type |
catalog.nodes | List Nimbus pipeline node types (data, preprocessing, features, models...). Use catalog.node_schema(node_type) for one node's full config schema and ports. Inputs: category |
catalog.template | Full template incl. the 'train' execGraph needed by execution.run/pipeline.validate. Inputs: template_id |
catalog.templates | List built-in starter pipelines (MI/P300/SSVEP...). catalog.template(id) returns the graph. Each row carries ``datasetId`` (catalog id, e.g. "BNCI2014_001" — the id catalog.leaderboard and catalog.datasets use) and ``paradigm`` when the tem Inputs: dataset, paradigm |
data.delete_upload | Delete an uploaded file from your account (disk + registry). Requires confirm=True. Pass the path returned by data.upload (file.path). Only your own uploads can be deleted; missing paths return not-found. Inputs: path, confirm |
data.inspect_dataset | Exploratory summary of a public EEG dataset (MOABB pack): channels, sampling rate, trial/class balance, per-channel µV stats, band powers and a PSD overview. Look at the data BEFORE building pipelines: class balance drives stratification ch Inputs: dataset, subject, mode |
data.inspect_file | Exploratory summary of an EEG file (.edf/.bdf/.mat/.csv/.tsv/.txt/.h5): channels, sampling rate, trial/class balance, per-channel µV stats, band powers and a PSD overview. The path shape picks the source: ABSOLUTE path → read the file from Inputs: path, sampling_rate |
data.upload | Upload an EEG file (.edf/.bdf/.mat/.csv/.txt/.tsv/.h5/.hdf5, <=500MB) to the backend and get the registered path for a custom_data node. sampling_rate (Hz, e.g. 250.0) is REQUIRED for plain CSV/TSV/TXT files without embedded metadata — uplo Inputs: file_path, dataset_name, sampling_rate, format |
device.list | EEG devices supported by this backend (OpenBCI, Muse, BrainBit, LSL, PiEEG...). |
device.test | Test a device connection WITHOUT starting a stream (safe, no confirm needed). Inputs: device_type, connection_type, port, ip_address, ip_port, stream_name |
execution.artifacts | Trained artifacts (models/filters, e.g. *.pkl) saved by an execution. Inputs: execution_id |
execution.cancel | Cancel a running execution. Inputs: execution_id |
execution.delete | Permanently delete one of your finished runs (completed/failed/cancelled) with its results. Running runs must be cancelled first (409 nimbus.execution.delete_not_terminal). Owner only. Inputs: execution_id, confirm |
execution.download_artifact | Download one artifact file. Local/stdio: saved to NIMBUS_EXPORT_DIR/executions/<id>/ and its path returned. Hosted gateway: returned inline as ``contentBase64`` (up to 1 MB of base64); larger files point to Nimbus Studio. Nothing is written Inputs: execution_id, artifact_name |
execution.get | Execution status summary (status: running/completed/failed/cancelled). Summary fields: ``dataset`` is the human-readable display label (e.g. "BCIIV2a"); ``datasetId`` is the catalog id (e.g. "BNCI2014_001") accepted by other tools (data.ins Inputs: execution_id |
execution.list | Recent executions. Optional status filter (running/completed/failed/cancelled). Per-run fields: ``dataset`` is the human-readable display label (e.g. "BCIIV2a"); ``datasetId`` is the catalog id (e.g. "BNCI2014_001") accepted by other tools Inputs: limit, status |
execution.results | Metrics for a completed run. Trimmed by default (accuracy, kappa, ITR, confusion matrix, per-class); full=True returns the complete result object. Inputs: execution_id, full |
execution.run | Start a pipeline run (NON-BLOCKING). Returns executionId — poll with execution.get() until status is completed/failed, then execution.results(). If an identical graph is already running for you, the run still starts but the response carries Inputs: train_graph, name, description, subject, layout |
experiment.delete | Delete one of your experiment records (server + this machine's local cache). Its individual runs are kept — delete them with execution.delete. A still-running experiment cannot be deleted. Inputs: experiment_id, confirm |
experiment.get | Experiment snapshot: status (running/completed/failed), per-run rows ({name, executionId, status, error?, metrics?, evaluationKind?}) and, once finished, aggregates over completed runs only: per-metric {mean, std, best, n}, plus ``pooledExe Inputs: experiment_id |
experiment.run | Run 1-25 pipelines as ONE paced experiment (NON-BLOCKING). Returns an experimentId immediately; a background thread submits at most 2 runs at a time (min(max_concurrent, 2)), retries queue-full up to 3 times per run, and polls each executio Inputs: runs, max_concurrent |
foundation.compare | Run every available pretrained backbone on YOUR data and see which wins — a ranked bar chart with CI whiskers, params, and wall time per backbone. Backbones that can't process your data (window size, channel count) are noted, not silently s Inputs: source, dataset, subject, mode, path |
leaderboard.mine | List your leaderboard submissions (newest first), all datasets. |
leaderboard.status | Fetch one of your leaderboard submissions (owner-only). Returns status (queued | scoring | done | failed), metrics when done (meanAccuracyPct + CI, same shape as leaderboard rows), or the error that failed it. Inputs: submission_id |
leaderboard.submit | Submit a BYO python_model to a leaderboard track for server-side scoring. Nimbus scores it server-side under the track's fixed protocol — you submit code, never results. Poll ``leaderboard.status`` with the returned ``submissionId``; scorin Inputs: dataset_id, name, code, class_name, requirements, track |
pipeline.export | Export the pipeline as a standalone runnable Python bundle (zip). Local/stdio: the zip is saved under NIMBUS_EXPORT_DIR/exports and its path returned. Hosted gateway: the zip is returned inline as ``contentBase64`` (up to 1 MB of base64). U Inputs: train_graph, name |
pipeline.validate | Validate a pipeline graph before running. ExecGraphSnapshot: {nodes: [{id, type, config}], connections: [{from, to}]}. Build it from catalog.template(id).train or from scratch using catalog.nodes(). Inputs: train_graph |
pipeline.validate_node | Validate one node's config (schema + semantic checks). Catches the same value errors as pipeline.validate for a single node (inverted bandpass, CSP components vs channel count when dataset is set). Inputs: node_type, config, dataset |
plots.confusion | Confusion-matrix figure for one execution: heatmap with trial counts + per-class accuracy bars, rendered as a PNG the assistant can see. Use it right after execution.results to eyeball WHICH classes are confused, not just the accuracy numbe Inputs: execution_id, matrix, save |
plots.dataset | Figure over an EEG data source — the visual companion to data.inspect_dataset. kind=psd (Welch, channel mean bold), kind=bandpower (channel × band dB heatmap), kind=topomap (band-power scalp map), kind=spectrogram (time-frequency for one ch Inputs: kind, source, dataset, subject, mode, path |
plots.erp, plots.leaderboard, project.create, project.delete, project.list, project.load, project.rename, project.save, protocol.export_stats, protocol.list, protocol.pause, protocol.resume, protocol.save, protocol.session_status, protocol.start_assignment, protocol.stop, protocol.validate, python.validate, stats.grouped, stream.start, stream.status, stream.stop, stream.telemetry
Every block below points at https://nimbus-mcp.fly.dev/mcp. Pick your client and copy.
claude mcp add --transport http nimbus-bci https://nimbus-mcp.fly.dev/mcp
{
"mcpServers": {
"nimbus-bci": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://nimbus-mcp.fly.dev/mcp"]
}
}
}{
"mcpServers": {
"nimbus-bci": {
"url": "https://nimbus-mcp.fly.dev/mcp"
}
}
}{
"servers": {
"nimbus-bci": {
"type": "http",
"url": "https://nimbus-mcp.fly.dev/mcp"
}
}
}{
"context_servers": {
"nimbus-bci": {
"url": "https://nimbus-mcp.fly.dev/mcp"
}
}
}{
"mcpServers": {
"nimbus-bci": {
"serverUrl": "https://nimbus-mcp.fly.dev/mcp"
}
}
}{
"mcpServers": {
"nimbus-bci": {
"url": "https://nimbus-mcp.fly.dev/mcp"
}
}
}name: Nimbus BCI
version: 0.0.1
schema: v1
mcpServers:
- name: Nimbus BCI
type: streamable-http
url: https://nimbus-mcp.fly.dev/mcp{
"mcpServers": {
"nimbus-bci": {
"httpUrl": "https://nimbus-mcp.fly.dev/mcp"
}
}
}{
"mcpServers": {
"nimbus-bci": {
"type": "http",
"url": "https://nimbus-mcp.fly.dev/mcp"
}
}
}{
"mcpServers": {
"nimbus-bci": {
"url": "https://nimbus-mcp.fly.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fnimbus-mcp.fly.dev%2Fmcp&type=streamable_http&id=nimbus-bci&name=Nimbus%20BCI
It answered our last check on 21 November 2026 in 4332 ms. Over 4 checks since 5 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
63, as returned by the server's own tools/list on 21 November 2026: account.whoami, bids.export_dataset, bids.export_execution, calibration.pause, calibration.resume, calibration.start, calibration.status, calibration.train, and 55 more.
It answered our last check on 21 November 2026 in 4332 ms. Over 4 checks since 5 October 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://nimbus-mcp.fly.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.nimbusbci. Endpoint host: nimbus-mcp.fly.dev. ARD identifier: urn:air:io.github.nimbusbci:mcp:nimbus-mcp.
First indexed 4 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.