List your agent

Nimbus BCI

MCP server● Hosted · onlineInstallablev0.14.21

BCI/EEG toolkit: public MOABB/BNCI datasets, pipeline build/validate, hosted training, BIDS export

Reviews

No review yet. Used Nimbus BCI? Be the first to help others choose.

What it does

Nimbus BCI is an MCP server, a connector that lets an AI assistant use it as a tool. It can be used hosted (nothing to install) or installed locally.

No capability identified yet from its description.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.

At a glance

Hosted (remote)YES
Local installYES
Version0.14.21
PackagesPyPI
PriceNot in the registry
First seen04 Oct 2026
Last checked2d ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 7h ago (live check)

Hosted endpoint

  • https://nimbus-mcp.fly.dev/mcp streamable-http

In Claude Code: claude mcp add --transport http nimbus-bci https://nimbus-mcp.fly.dev/mcp

Install package

  • PYPI nimbus-mcp v0.14.21 · runs locally (stdio)

MCP settings (Claude Desktop, Cursor and other MCP clients)

{
  "mcpServers": {
    "nimbus-bci": {
      "url": "https://nimbus-mcp.fly.dev/mcp"
    }
  }
}

Reliability

Re-tested about every 3 days · last check 7h ago
100%Observed availability, 30 days · 10 checks
10 / 0Answers / failures, 30 days
No key neededAccess status (latest answer)
Observed test history · one mark = one check
22 Oct18 Nov
AnsweredAnswered, key requiredNo valid answer

Observed endpoint availability: the share of our conclusive checks that got an answer. A request for a key or sign-in counts as an answer (the server is up, its access is protected). Timeouts, unreachable endpoints, server errors and invalid MCP replies count as failures; rate-limited checks and checks during our own incidents are not counted. This is what we observed at each check, not continuous uptime: an outage between two checks may go unseen. The 90-day figure will appear once 90 days of checks exist (checks since 19 Oct 2026). How we measure

Tool changes

Tool tracking since 13 Nov 2026 · test history since 19 Oct 2026

No tool added or removed since tracking started. 63 tools in the latest list.

Changes are confirmed by comparing complete tool lists only, read about every 3 days, and dated by the day we saw them. A renamed tool appears as one removal and one addition.

Live check

Electra Index connected to the hosted endpoint 7h ago

ONLINE Nimbus BCI answered an MCP connection on 18 Nov 2026 and introduced itself as nimbus 0.14.21 (MCP protocol 2025-06-18).

63 tools offered to AI assistants

  • 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
  • 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.
  • catalog.node_schema · Full config JSON schema + input/output ports for one node type.
  • 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
  • catalog.template · Full template incl. the 'train' execGraph needed by execution.run/pipeline.validate.
  • catalog.datasets · Curated public EEG datasets (MOABB packs) available to pipelines.
  • 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;
  • 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
  • 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.
  • leaderboard.mine · List your leaderboard submissions (newest first), all datasets.
  • 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().
  • 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).
Show 51 more
  • 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
  • execution.cancel · Cancel a running execution.
  • 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.
  • 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
  • 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
  • execution.results · Metrics for a completed run. Trimmed by default (accuracy, kappa, ITR, confusion matrix, per-class); full=True returns the complete result object.
  • 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
  • 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.
  • calibration.pause · Pause a running calibration between trials (cues hold; resume anytime).
  • calibration.resume · Resume a paused calibration session.
  • 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
  • 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
  • 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.
  • 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
  • execution.artifacts · Trained artifacts (models/filters, e.g. *.pkl) saved by an execution.
  • 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
  • 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
  • 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;
  • 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/
  • 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).
  • stream.start · Connect an EEG device and START a live streaming session on the user's head. Requires confirm=True; call device.test first. Track with stream.status(). Idle watchdog: if no stream.status()/stream.telemetry() poll happens for idle_timeout_se
  • stream.status · Live snapshot of a streaming session (running, deviceConnected). Polling this also feeds the idle watchdog: each call resets the session's idle timer (see stream.start's idle_timeout_sec).
  • stream.stop · Stop a streaming session and disconnect the device (always safe to call). Also removes the session from the idle watchdog so it cannot fire after an explicit stop.
  • 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
  • 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
  • plots.erp · ERP butterfly figure from epoched data: one subplot per class, all channel means (thin) + across-channel mean (bold), time-locked to the trial event. Shows whether class-conditioned evoked structure exists BEFORE training anything.
  • plots.leaderboard · Leaderboard bar chart for one dataset: accuracy with 95% CI whiskers, best first; BYO python_model submissions highlighted in a distinct color. The visual companion to catalog.leaderboard. On the pretrained_few_trial track the figure also i
  • stream.telemetry · Live snapshot of a streaming session: latest prediction + recent window, signal quality (meanChannelQuality, snrDb, artifactProbability), indicators, running stats. Poll this while a session runs. Works with OR without a deployed model: mod
  • 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
  • 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.
  • 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
  • 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
  • project.create · Create a project (container for one pipeline document). Returns projectId.
  • project.list · List projects owned by the current principal (agent work included).
  • project.save · Save a pipeline graph into a project (visible on the studio canvas). Always pass expected_revision from the last project.load (or a prior save/create response). When it does not match the current server revision, the save fails with a confl
  • project.load · Load a project's saved pipeline (train graph + meta) for editing/re-running.
  • project.rename · Rename a project you own (max 200 characters).
  • project.delete · Delete a project (and its saved pipeline document) from the studio workspace. Requires confirm=True: this removes the project from the user's project list. Executions already run from it are not affected. Find ids with project.list.
  • protocol.validate · Validate a neurofeedback protocol document WITHOUT saving it. Returns {valid: true, spec} on success, or {valid: false, errors: [...]} with the per-violation list (loc/msg) when the document is invalid — the verdict is data, never an except
  • protocol.save · Validate and persist the NEXT VERSION of a protocol document (confirm-gated: each call appends a version row; accidental calls clutter the version history). Edits create a new version — the assignment pins the version it runs.
  • protocol.list · Every saved protocol id at its latest version.
  • protocol.start_assignment · Enroll a subject and prepare their neurofeedback deploy session (confirm-gated — a session runs on a human). Creates the assignment (yoked sham arms REQUIRE yoked_donor_upload_id: a recorded simulated session's upload — mint one by running
  • protocol.session_status · Live snapshot of a protocol deploy session: the scheduler block / session progress + threshold state (under ``protocol``) beside the telemetry window (recent indicators, quality, stats).
  • protocol.pause · Pause a running protocol session (blocks freeze; the session and device stay alive — resume with protocol.resume). Simulated and playback sessions only while paused: no data is recorded.
  • protocol.resume · Resume a paused protocol session (restarts the server-driven device loop). Live-hardware resume requires a Pro plan; simulated sessions are free. Pass the session's channel count (start_assignment reports it).
  • protocol.stop · Stop a protocol session (always safe to call): stops streaming, saves the block-annotated recording, advances the assignment when the scheduler reached its natural end, and disconnects the device (best-effort — a failed disconnect is report
  • protocol.export_stats · Paired pre/post analysis for one assignment's recorded sessions: per-block aggregates (descriptive + CSV), paired t / Wilcoxon / dz (per-statistic minimums: paired t and Cohen's dz need ≥ 3 completed sessions, Wilcoxon needs ≥ 5), specifici
  • python.validate · Statically check a python_model script (BYO model class) without running it. Compiles the source and verifies the contract — a class with fit(X, y, info) and predict(X); optional predict_proba(X) unlocks confidence panels. Never executes th
  • stats.grouped · Cluster-aware group statistics across executions. REQUIREMENT (read first): each execution must have been run with an evaluation plan that STORED per-SUBJECT accuracies for at least 3 subjects — e.g. leave-one-subject-out (LOSO) or grouped
  • 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

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Re-tested about every 3 days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Facts & evidence

Each fact shows where it was seen and when.
FactValueEvidenceSourceLast confirmed
Install packagenimbus-mcpDECLAREDSRC-001 Official MCP Registry2d ago
Version0.14.21DECLAREDSRC-001 Official MCP Registry2d ago
Hosted endpointhttps://nimbus-mcp.fly.dev/mcpDECLAREDSRC-001 Official MCP Registry2d ago
Remote access (hosted)yesDECLAREDSRC-001 Official MCP Registry2d ago
Package registriespypiDECLAREDSRC-001 Official MCP Registry2d ago
Local install (package)yesDECLAREDSRC-001 Official MCP Registry2d ago
Repositoryhttps://github.com/nimbusbci/nimbus-mcpDECLAREDSRC-001 Official MCP Registry2d ago
Registry statusactiveDECLAREDSRC-001 Official MCP Registry2d ago
MCP serveryesDECLAREDSRC-001 Official MCP Registry2d ago

Change history

  • VERSION03 Nov 2026
    0.14.20 → 0.14.21
  • VERSION02 Nov 2026
    0.14.19 → 0.14.20
  • VERSION30 Oct 2026
    0.14.18 → 0.14.19
  • VERSION29 Oct 2026
    0.14.17 → 0.14.18
  • VERSION23 Oct 2026
    0.14.15 → 0.14.17
  • VERSION21 Oct 2026
    0.14.11 → 0.14.15
  • VERSION20 Oct 2026
    0.14.8 → 0.14.11
  • VERSION19 Oct 2026
    0.14.4 → 0.14.8
  • VERSION18 Oct 2026
    0.14.3 → 0.14.4
  • VERSION18 Oct 2026
    0.14.2 → 0.14.3
  • VERSION16 Oct 2026
    0.14.1 → 0.14.2
  • VERSION16 Oct 2026
    0.14.0 → 0.14.1
  • VERSION16 Oct 2026
    0.13.2 → 0.14.0
  • VERSION14 Oct 2026
    0.13.1 → 0.13.2
  • VERSION14 Oct 2026
    0.13.0 → 0.13.1
  • VERSION13 Oct 2026
    0.12.1 → 0.13.0
  • VERSION10 Oct 2026
    0.12.0 → 0.12.1
  • VERSION10 Oct 2026
    0.11.0 → 0.12.0
  • VERSION10 Oct 2026
    0.10.0 → 0.11.0
  • VERSION09 Oct 2026
    0.9.2 → 0.10.0
  • VERSION08 Oct 2026
    0.9.1 → 0.9.2
  • VERSION08 Oct 2026
    0.9.0 → 0.9.1
  • VERSION08 Oct 2026
    0.8.1 → 0.9.0
  • VERSION05 Oct 2026
    0.8.0 → 0.8.1
  • VERSION05 Oct 2026
    0.7.0 → 0.8.0
  • VERSION05 Oct 2026
    0.6.1 → 0.7.0
  • VERSION05 Oct 2026
    0.6.0 → 0.6.1
  • CHANGED04 Oct 2026
    remote access: no → yes
  • VERSION04 Oct 2026
    0.5.1 → 0.6.0
  • NEW04 Oct 2026
    first seen in the index

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Do you run Nimbus BCI? Know when it stops answering

For publishers · optional

Its hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.

Monitor Nimbus BCILaunch offer $39.99 once, for life instead of $9.99/month · All plans

Monitoring never changes a score or a rank.

Are you the publisher of Nimbus BCI?

Free · show your listing

An independent listing builds trust with your buyers. Announce it, and add the badge to your website or README.

Announce it on LinkedIn
Listed on Electra IndexListed on Electra Index
<a href="https://electraindex.com/mcp/nimbus-bci?utm_source=badge&utm_medium=share&utm_campaign=listing"><img src="https://electraindex.com/api/badge/nimbus-bci/card" width="260" height="72" alt="Listed on Electra Index"></a>

Questions about Nimbus BCI

How do I connect Nimbus BCI?

Use the hosted endpoint https://nimbus-mcp.fly.dev/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

What tools does Nimbus BCI offer?

When Electra Index connected on 18 Nov 2026, it listed 63 tools: account.whoami, catalog.nodes, catalog.node_schema, catalog.templates, catalog.template, catalog.datasets, catalog.leaderboard, leaderboard.submit and more. The full list is in "Live check" above.

Is Nimbus BCI online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 7h ago.