MCP servers › io.github.nimbusbci › nimbus-mcp

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.nimbusbci/nimbus-mcp

AI agents build, train, and analyze BCI/EEG pipelines: data, models, experiments, live sessions. — the publisher's description

7 of 8 record checks metRead-only · tools listed 2026-10-23Topic: science-health-and-education · AI-classifiedversion 0.14.15PythonOther/Proprietary Licensestandard input/output, streamable HTTP60 tools

Summary

io.github.nimbusbci/nimbus-mcp is a remote and local MCP server listed in the official MCP registry at version 0.14.15. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 60 tools, 0 resources and 0 prompts.

Record checks

7 of 8 record checks met · 1 does not apply

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#1,876 of 15,112 packages by monthly downloads
Not ranked by stars: 3 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote and local package
Transport: standard input/output, streamable HTTP
Package: PyPI · listed version behind the latest release
License: Other/Proprietary License
Dependencies: no known high or critical advisories
Repository: public
Tools: 60
Described as changing data: 27 of 60 toolsAI-classified
Mainly works on: files and code on the machine it runs onAI-classified
Topic: science-health-and-educationAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

27 tools are described as changing something (leaderboard.submit, execution.run, execution.cancel, …): our AI model's reading of the descriptions, not something we tested. We did not call them.
The registry lists 0.14.15; 0.14.17 is newer (2 releases).

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested

yes, a real session (not a text-only review)

Last tested

2026-10-23

Mode

read-only (no tool calls)

Latest version

0.14.15, published 2026-10-21 (registry, as of the 2026-10-23 snapshot)

First listed version

2026-10-04 (earliest version still in the registry; older removed versions would be earlier)

Version history

24 versions listed, 2026-10-04 to 2026-10-21; 24 in the 90 days before the 2026-10-23 snapshot.

Most recent 12 versions

0.14.15 · 2026-10-21
0.14.11 · 2026-10-20
0.14.8 · 2026-10-19
0.14.4 · 2026-10-18
0.14.3 · 2026-10-18
0.14.2 · 2026-10-16
0.14.1 · 2026-10-16
0.14.0 · 2026-10-16
0.13.2 · 2026-10-14
0.13.1 · 2026-10-14
0.13.0 · 2026-10-13
0.12.1 · 2026-10-10

(versions still listed in the registry only)

Registry data

snapshot 2026-10-23

Package and repository

checked 2026-10-23

Engine

mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.14.15 (published 2026-10-21).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

60tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on.

27 of 60 tools are described as changing something (creating, editing, deleting, sending or running).

account.whoamireads or searches
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
catalog.nodesreads or searches
“List Nimbus pipeline node types (data, preprocessing, features, models...).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input
- categorystring or null“Optional filter — e.g.”
catalog.node_schemareads or searches
“Full config JSON schema + input/output ports for one node type.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- node_typestringrequired“Node id from catalog.nodes (e.g.”
catalog.templatesreads or searches
“List built-in starter pipelines (MI/P300/SSVEP...).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
catalog.templatereads or searches
“Full template incl.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- template_idstringrequired“Template id from catalog.templates (e.g.”
catalog.datasetsreads or searches
“Curated public EEG datasets (MOABB packs) available to pipelines.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input
- only_on_diskboolean“Only return datasets whose data packs are present on this backend (True by default; False also lists known-but-missing sets).”
catalog.leaderboardreads or searches
“Public benchmark leaderboard: pipeline rankings per dataset.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input
- dataset_idstring or null“Optional dataset id.”
leaderboard.submitdescribed as changing data
“Submit a BYO python_model to a leaderboard track for server-side scoring.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
11 inputs, 2 required
- dataset_idstringrequired“A dataset id from catalog.leaderboard ``submittableDatasets`` (e.g.”
- namestringrequired“Display name on the board (<=100 chars).”
- codestring or null“Python source defining a class with fit(X, y, info) and predict(X) (<=256KB; validate first with python.validate).”
- class_namestring or null“Contract class to instantiate; omit to auto-detect.”
- requirementsarray or null“Optional PyPI requirements (e.g.”
- trackstring“"cross_subject" (default — full-data leave-one-subject-out, seed 42) or "pretrained_few_trial" (efficiency track: LOSO with a protocol-fixed 100-trials-per-sub…”
- verificationstring“"verified" (default; server-side scored, Pro on the hosted backend) or "unverified_local" (Account-Free locally-computed lane; see the tool description for its…”
- backbone_kindstring or null“Checkpoint family for the BYO backbone lane — one of the zoo's supported kinds (e.g.”
- backbone_repostring or null“HF 'org/name' repo id for the BYO backbone lane.”
- backbone_revisionstring or null“Full 40-char commit SHA pinning the backbone.”
- backbone_licensestring or null“License declared for the backbone checkpoint.”
leaderboard.statusreads or searches
“Fetch one of your leaderboard submissions (owner-only).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- submission_idstringrequired“The submissionId returned by leaderboard.submit.”
leaderboard.minereads or searches
“List your leaderboard submissions (newest first), all datasets.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
pipeline.validatecalculates or converts
“Validate a pipeline graph before running.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- train_graphobjectrequired“The graph to validate ({nodes, connections}).”
pipeline.validate_nodecalculates or converts
“Validate one node's config (schema + semantic checks).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
- node_typestringrequired“Node type id from catalog.nodes (e.g.”
- configobjectrequired“The node's config object to check.”
- datasetstring or null“Optional MOABB pack id (e.g.”

Show 48 more tools

execution.runruns code or commandsdescribed as changing data
“Start a pipeline run (NON-BLOCKING).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
- train_graphobjectrequired“Pipeline graph {nodes: [{id, type, config}], connections: [{from, to}]} as built by catalog.template/pipeline.validate.”
- namestring or null“Display name for the run (shown in the Runs list).”
- descriptionstring or null“Optional longer description of the experiment.”
- subjectstring or null“Optional dataset subject code (e.g.”
- layoutobject or null“Optional canvas positions {nodes: {id: {x, y}}}; a deterministic grid is synthesized when omitted.”
execution.cancelruns code or commandsdescribed as changing data
“Cancel a running execution.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
1 input, 1 required
- execution_idstringrequired“The run to terminate (from execution.run/execution.list).”
execution.getreads or searches
“Execution status summary (status: running/completed/failed/cancelled).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- execution_idstringrequired“The run to check (from execution.run/execution.list).”
execution.listreads or searches
“Recent executions.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
- limitinteger“Maximum number of runs to return (default 20).”
- statusstring or null“Filter by run status: running/completed/failed/cancelled.”
execution.resultsreads or searches
“Metrics for a completed run.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- execution_idstringrequired“The completed run to fetch metrics for.”
- fullboolean“Return the backend's complete result object (all fields).”
calibration.startruns code or commandsdescribed as changing data
“Start a guided subject calibration session (NON-BLOCKING; confirm-gated — the device goes on a human's head).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
14 inputs
- paradigmstring“mi | p300 | sart | target_hit.”
- confirmboolean“MUST be true — explicit user go-ahead for a session on their head.”
- trials_per_classinteger or null“Override the template's trial count (minimum 5).”
- classesarray or null“Override class list [{id,label,cue}] (MI default: left/right hand).”
- namestring or null“Display name recorded on the execution.”
- device_typestring or null“Device id from device.list (omit → template default synthetic).”
- connection_typestring or null“Device selector when several exist (e.g.”
- portstring or null“Serial/COM port for wired devices.”
- ip_addressstring or null“Device IP for network/wifi devices.”
- ip_portinteger or null“Port for network devices.”
- stream_namestring or null“LSL stream name (LSL devices).”
- source_idstring or null“LSL source id.”
- mac_addressstring or null“Bluetooth MAC (BT devices).”
- serial_numberstring or null“Device serial (some BLE stacks).”
calibration.statusreads or searches
“Live snapshot of a calibration session (phase, current trial, progress, paused).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- execution_idstringrequired“The calibration run to inspect (from calibration.start).”
calibration.pauseruns code or commandsdescribed as changing data
“Pause a running calibration between trials (cues hold; resume anytime).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- execution_idstringrequired“The calibration run to pause.”
calibration.resumeruns code or commandsdescribed as changing data
“Resume a paused calibration session.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- execution_idstringrequired“The calibration run to resume.”
calibration.trainruns code or commandsdescribed as changing data
“Train the subject's own classifier from a COMPLETED calibration session (NON-BLOCKING).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
- execution_idstringrequired“The COMPLETED calibration run (from calibration.start).”
- paradigmstring“Paradigm of the recording (mi | p300 | sart | target_hit); mi and p300 have default train templates.”
- template_idstring or null“Train template to use (e.g.”
- train_graphobject or null“Explicit train graph instead of a template; its first data node (custom_data/public_data) is rewired onto the recording.”
- namestring or null“Display name recorded on the training run.”
experiment.runruns code or commandsdescribed as changing data
“Run 1-25 pipelines as ONE paced experiment (NON-BLOCKING).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
- runsarrayrequired“1-25 entries, each {name: str, train_graph: {nodes, connections}} (same graph shape as execution.run's train_graph).”
- max_concurrentinteger“Parallel submissions cap, clamped to 1-2 (default 2).”
experiment.getreads or searches
“Experiment snapshot: status (running/completed/failed), per-run rows ({name, executionId, status, error?, metrics?, evaluationKind?}) and, once finished, aggregates over completed runs only: per-metr…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- experiment_idstringrequired“The experiment to inspect (from experiment.run).”
execution.artifactsreads or searches
“Trained artifacts (models/filters, e.g.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- execution_idstringrequired“Run whose artifacts to list.”
execution.download_artifactreads or searches
“Download one artifact file to NIMBUS_EXPORT_DIR/executions/<id>/ and return its path.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
- execution_idstringrequired“Run that produced the artifact.”
- artifact_namestringrequired“File name from execution.artifacts (e.g.”
pipeline.exportdescribed as changing data
“Export the pipeline as a standalone runnable Python bundle (zip saved locally).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- train_graphobjectrequired“Pipeline graph {nodes, connections} to export.”
- namestring or null“Optional name recorded inside the bundle.”
bids.export_datasetdescribed as changing data
“Export a Nimbus dataset as a BIDS-layout zip saved to NIMBUS_EXPORT_DIR/bids/.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- datasetstringrequired“Dataset id — a MOABB pack id (e.g.”
- subjectsarray or null“Pack exports only — subject filter (e.g.”
- kindstring or null“Optional explicit source kind: pack|upload|recording (default auto).”
bids.export_executiondescribed as changing data
“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)…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
1 input, 1 required
- execution_idstringrequired“Run whose results to export (from execution.run).”
device.liston 1 other serverreads or searches
“EEG devices supported by this backend (OpenBCI, Muse, BrainBit, LSL, PiEEG...).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
device.testreads or searches
“Test a device connection WITHOUT starting a stream (safe, no confirm needed).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
9 inputs, 1 required
- device_typestringrequired“Device id from device.list (e.g.”
- connection_typestring or null“Device-specific selector when several exist (e.g.”
- portstring or null“Serial/COM port for wired devices.”
- ip_addressstring or null“Device IP for network/wifi devices.”
- ip_portinteger or null“Port for network devices.”
- stream_namestring or null“LSL stream name (LSL devices).”
- source_idstring or null“LSL source id.”
- mac_addressstring or null“Bluetooth MAC (BT devices).”
- serial_numberstring or null“Device serial (some BLE stacks).”
stream.startdescribed as changing data
“Connect an EEG device and START a live streaming session on the user's head.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
14 inputs, 1 required
- device_typestringrequired“Device id from device.list (e.g.”
- confirmboolean“MUST be true to start — the explicit user go-ahead for a live session on their head; anything else is refused with zero requests.”
- session_idstring or null“Optional existing session to resume/reuse.”
- chunk_sizeinteger“Samples per streamed chunk (default 125).”
- n_channelsinteger“Channel count to open (default 8).”
- connection_typestring or null“Device-specific selector (e.g.”
- portstring or null“Serial/COM port for wired devices.”
- ip_addressstring or null“Device IP for network/wifi devices.”
- ip_portinteger or null“Port for network devices.”
- stream_namestring or null“LSL stream name (LSL devices).”
- source_idstring or null“LSL source id.”
- mac_addressstring or null“Bluetooth MAC (BT devices).”
- serial_numberstring or null“Device serial (some BLE stacks).”
- idle_timeout_secinteger“Watchdog: stop+disconnect after this many seconds without a status poll (default 900; 0 disables).”
stream.statusreads or searches
“Live snapshot of a streaming session (running, deviceConnected).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- session_idstringrequired“The streaming session to inspect.”
stream.stopdescribed as changing data
“Stop a streaming session and disconnect the device (always safe to call).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
1 input, 1 required
- session_idstringrequired“The streaming session to stop.”
plots.confusiongenerates contentdescribed as changing data
“Confusion-matrix figure for one execution: heatmap with trial counts + per-class accuracy bars, rendered as a PNG the assistant can see.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- execution_idstringrequired“Run to plot (from execution.run / execution.results).”
- matrixstring“"eval" (held-out, default) or "train" (fit-set / cross-validation).”
- saveboolean“Also write the PNG to NIMBUS_EXPORT_DIR/plots/ and return its path.”
plots.datasetgenerates contentdescribed as changing data
“Figure over an EEG data source — the visual companion to data.inspect_dataset.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
9 inputs, 2 required
- kindstringrequired“Figure type: psd | topomap | bandpower | spectrogram.”
- sourcestringrequired“"dataset" (MOABB pack), "upload" (path from data.upload), or "local" (absolute path, local backend only).”
- datasetstring or null“MOABB dataset id, e.g.”
- subjectstring or null“Subject id, e.g.”
- modestring“Pack split to load: training | evaluation | all (source=dataset).”
- pathstring or null“Upload path (source=upload) or absolute local path (source=local).”
- bandstring“Band for kind=topomap: delta|theta|alpha|beta|gamma (default alpha).”
- channel_idxinteger“0-based channel for kind=spectrogram (default 0).”
- saveboolean“Also write the PNG to NIMBUS_EXPORT_DIR/plots/ and return its path.”
plots.erpgenerates contentdescribed as changing data
“ERP butterfly figure from epoched data: one subplot per class, all channel means (thin) + across-channel mean (bold), time-locked to the trial event.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
7 inputs, 1 required
- sourcestringrequired“"dataset" (MOABB pack), "upload" (path from data.upload), or "local" (absolute path, local backend only).”
- datasetstring or null“MOABB dataset id, e.g.”
- subjectstring or null“Subject id, e.g.”
- modestring“Pack split to load: training | evaluation | all (source=dataset).”
- pathstring or null“Upload path (source=upload) or absolute local path (source=local).”
- max_channelsinteger“Channels drawn per class subplot (default 16, max 64).”
- saveboolean“Also write the PNG to NIMBUS_EXPORT_DIR/plots/ and return its path.”
plots.leaderboardgenerates contentdescribed as changing data
“Leaderboard bar chart for one dataset: accuracy with 95% CI whiskers, best first; BYO python_model submissions highlighted in a distinct color.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- dataset_idstringrequired“Dataset to chart, e.g.”
- trackstring“"within_session" (curated 5-fold), "crossSubject" (LOSO, curated + BYO submissions), or "pretrained_few_trial" (the efficiency track: LOSO at the protocol's fi…”
- saveboolean“Also write the PNG to NIMBUS_EXPORT_DIR/plots/ and return its path.”
stream.telemetryreads or searches
“Live snapshot of a streaming session: latest prediction + recent window, signal quality (meanChannelQuality, snrDb, artifactProbability), indicators, running stats.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- session_idstringrequired“The streaming session to read telemetry for.”
- windowinteger“How many recent predictions/chunks to include (default 50).”
data.uploadcreates or changes datadescribed as changing data
“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.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 1 required
- file_pathstringrequired“Local file to upload (.edf/.bdf/.mat/.csv/.txt/.tsv/.h5/.hdf5, <=500MB).”
- dataset_namestring or null“Optional label for the uploaded dataset.”
- sampling_ratenumber or null“Hz for headerless CSV/TSV/TXT (REQUIRED there, e.g.”
- formatstring or null“Override extension-based detection (auto|mat|csv|tsv|txt|edf|bdf|h5|hdf5).”
data.delete_uploaddeletesdescribed as changing data
“Delete an uploaded file from your account (disk + registry).”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
2 inputs, 1 required
- pathstringrequired“Upload path from data.upload (e.g.”
- confirmboolean“MUST be true to delete — the explicit user go-ahead.”
data.inspect_datasetreads or searches
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- datasetstringrequired“Dataset id from catalog.datasets (e.g.”
- subjectstring or null“REQUIRED subject code ("S01") or comma-list cohort ("S01,S03").”
- modestring“Which split to summarize — training | evaluation | all.”
data.inspect_filereads or searches
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- pathstringrequired“ABSOLUTE filesystem path (`~` is expanded; local backends only) or the RELATIVE upload path returned by data.upload (works on any backend).”
- sampling_ratenumber or null“Hz for CSV/TSV/TXT files (REQUIRED there, e.g.”
project.createon 1 other servercreates or changes datadescribed as changing data
“Create a project (container for one pipeline document).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
- namestringrequired“Project display name (e.g.”
- descriptionstring or null“Optional longer description shown in the studio.”
project.liston 1 other serverreads or searches
“List projects owned by the current principal (agent work included).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
project.savecreates or changes datadescribed as changing data
“Save a pipeline graph into a project (visible on the studio canvas).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 3 required
- project_idstringrequired“Target project (from project.create/project.list).”
- train_graphobjectrequired“Pipeline graph {nodes, connections} to persist.”
- expected_revisionintegerrequired“Optimistic-concurrency base from project.load / a prior save.”
- namestring or null“Optional pipeline name stored on the document.”
- subjectstring or null“Optional dataset subject code (e.g.”
project.loadreads or searches
“Load a project's saved pipeline (train graph + meta) for editing/re-running.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- project_idstringrequired“Project whose pipeline document to load.”
project.deleteon 1 other serverdeletesdescribed as changing data
“Delete a project (and its saved pipeline document) from the studio workspace.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
2 inputs, 1 required
- project_idstringrequired“Project to delete (from project.create/project.list).”
- confirmboolean“MUST be true to delete — the explicit user go-ahead.”
protocol.validatecalculates or converts
“Validate a neurofeedback protocol document WITHOUT saving it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- specobjectrequired“Wire-format protocol document (camelCase): id, name, indicator {name, transform}, armDefaults, blocks [{id, kind: assessment|training, durationSec, feedback?}]…”
protocol.savecreates or changes datadescribed as changing data
“Validate and persist the NEXT VERSION of a protocol document (confirm-gated: each call appends a version row; accidental calls clutter the version history).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
- specobjectrequired“Wire-format protocol document (validate first to iterate).”
- confirmboolean“MUST be true to write.”
protocol.listreads or searches
“Every saved protocol id at its latest version.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
protocol.start_assignmentcreates or changes datadescribed as changing data
“Enroll a subject and prepare their neurofeedback deploy session (confirm-gated — a session runs on a human).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 4 required
- protocol_idstringrequired“Saved protocol id (protocol.save).”
- protocol_versionintegerrequired“Immutable version the assignment pins.”
- subject_labelstringrequired“Subject identifier (e.g.”
- armstringrequired“active | sham.”
- confirmboolean“MUST be true — explicit go-ahead for a session on a human.”
- yoked_donor_upload_idstring or null“Donor recording upload (required when the arm's blocks resolve to yoked — the backend validates coverage).”
- execution_idstring or null“Optional completed execution whose stored graph carries a protocol_session node; default clones the template.”
protocol.session_statusreads or searches
“Live snapshot of a protocol deploy session: the scheduler block / session progress + threshold state (under ``protocol``) beside the telemetry window (recent indicators, quality, stats).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- session_idstringrequired“The deploy session to inspect (from start_assignment).”
- windowinteger“How many recent predictions to include (1-200, default 50).”
protocol.pausecreates or changes datadescribed as changing data
“Pause a running protocol session (blocks freeze; the session and device stay alive — resume with protocol.resume).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- session_idstringrequired“The deploy session to pause.”
protocol.resumecreates or changes datadescribed as changing data
“Resume a paused protocol session (restarts the server-driven device loop).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
- session_idstringrequired“The deploy session to resume.”
- chunk_sizeinteger“Samples per streamed chunk (default 125).”
- n_channelsinteger“Session channel count (the built-in template opens 4).”
protocol.stopdescribed as changing data
“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 (be…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
- session_idstringrequired“The deploy session to stop.”
protocol.export_statsreads or searches
“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…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- assignment_idstringrequired“The assignment to analyze (from start_assignment).”
python.validatecalculates or converts
“Statically check a python_model script (BYO model class) without running it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- codestringrequired“Python source of the model class (<=256KB UTF-8).”
- class_namestring or null“Contract class to instantiate; omit to auto-detect the first class defining fit+predict.”
stats.groupedreads or searches
“Cluster-aware group statistics across executions.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- execution_idsarrayrequired“1–25 executions (from execution.run) to pool.”
- chancenumber or null“Chance level in [0, 1]; default 1/nClasses per execution.”
foundation.comparereads or searches
“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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
- sourcestringrequired“"dataset" (MOABB pack), "upload" (path from data.upload), or "local" (absolute path, local backend only).”
- datasetstring or null“MOABB dataset id, e.g.”
- subjectstring or null“Subject id, e.g.”
- modestring“Pack split to load: training | evaluation | all (source=dataset).”
- pathstring or null“Upload path (source=upload) or absolute local path (source=local).”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 60 tools
Says what it returns: 76% of 59 tools
States limits, defaults or errors: 6% of 49 tools
Says when to use it: 10% of 59 tools
Items covered per tool: 2.0 of 4 on average

Counted from the listing

Parameters with a description: 100% of 163
Tools with a description: 100% of 60
Typical description length: 318 characters

The tool set

Counted from the listing

Tools: 60
Size of the list: about 16,458 tokens for an agent to load (characters ÷ 4)
Naming: 60 of 60 names use mixed or other styles

AI reading: easy to mix up

No pair found.

The AI items cover 60 of 60 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the PyPI package nimbus-mcp

Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "nimbus-mcp": {
      "command": "uvx",
      "args": [
        "nimbus-mcp==0.14.15"
      ]
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "nimbus-mcp": {
      "command": "uvx",
      "args": [
        "nimbus-mcp==0.14.15"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "nimbus-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "nimbus-mcp==0.14.15"
      ]
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"nimbus-mcp","type":"stdio","command":"uvx","args":["nimbus-mcp==0.14.15"]}'

Claude Code

claude mcp add --transport stdio nimbus-mcp -- uvx nimbus-mcp==0.14.15

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -- uvx nimbus-mcp==0.14.15

Optional settings the entry also lists (left out above): NIMBUS_API_URL, NIMBUS_TOKEN, NIMBUS_TOKEN_FILE, NIMBUS_MCP_KEY, NIMBUS_MCP_KEY_FILE.
This runs the publisher's code on your machine (uvx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://nimbus-mcp.fly.dev/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

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

VS Code · .vscode/mcp.json

{
  "servers": {
    "nimbus-mcp": {
      "type": "http",
      "url": "https://nimbus-mcp.fly.dev/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"nimbus-mcp","type":"http","url":"https://nimbus-mcp.fly.dev/mcp"}'

Claude Code

claude mcp add --transport http nimbus-mcp https://nimbus-mcp.fly.dev/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://nimbus-mcp.fly.dev/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 0.14.15
Latest stable: 0.14.17
Status: behind the latest release (2 releases, 2 days)
Withdrawn: no

Source: pypi.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (OSV.dev). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha256-f3dbd77e7ddb462f5…
License: Other/Proprietary License

Source: the package registry · 2026-10-23.

Usage

Downloads: 1,355 in the last month

Source: pypistats.org · 2026-10-23.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint nimbus-mcp.fly.dev/mcp	No session could be opened when we tried	no session	our test · 2026-10-23
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 0.14.15 on PyPI	Exists and can be installed	matches	PyPI · 2026-10-23
Repository github.com/nimbusbci/nimbus-mcp	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.nimbusbci
GitHub owner: an organization (nimbusbci)

Repository: github.com/nimbusbci/nimbus-mcp
Stars: 3
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

7 of 8 record checks met · 1 does not apply

#1,876 of 15,112 packages by monthly downloads
Not ranked by stars: 3 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierOther/Proprietary License
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists; a newer one is out.
Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.nimbusbci/nimbus-mcp

Answered from the data above

Is io.github.nimbusbci/nimbus-mcp safe to install?

We do not rate servers as safe or unsafe. 7 of its 8 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. A newer stable release exists than the one listed. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 27 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Has io.github.nimbusbci/nimbus-mcp been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.nimbusbci/nimbus-mcp do?

It lists 60 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, run code or commands, generate content and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.nimbusbci/nimbus-mcp change or delete data?

27 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does io.github.nimbusbci/nimbus-mcp publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

No. The registry lists 0.14.15; the latest stable release on PyPI is 0.14.17.

Where is the source code of io.github.nimbusbci/nimbus-mcp?

In github.com/nimbusbci/nimbus-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.Exekiel179/mne-mcpMNE-MCPalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, generates content, reads or searchescompare with this one
io.github.Jayzilva/helionyxHelionyxalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, generates content, reads or searchescompare with this one
com.mcparmory/canvasalso has tools that calculates or converts, creates or changes data, deletes, generates content, reads or searchescompare with this one
io.github.yatuk/itu-mcpİTÜ MCPalso has tools that calculates or converts, creates or changes data, deletes, generates content, reads or searchescompare with this one
io.github.AImplifier/neuro-mcpalso has tools that calculates or converts, creates or changes data, deletes, generates content, reads or searchescompare with this one
io.github.KozakHou/project-bourneProject Bournealso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one

Active servers whose topic is also “science-health-and-education” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model. This server also has a remote test (0 of 18 applicable checks exercised).

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted the published package in an isolated sandbox (read-only mode)
2,935 msConnected after 0 redirects.
Read the inventory: 60 tools, 0 resources, 0 prompts.
3,939 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

science-health-and-education

AI-classified · 2026-10-23

Pricing modelAI-classified

not checked

no website in the registry entry

Programming language

Python

api.github.com · 2026-10-23

Hosting type

remote and local package

registry · 2026-10-23

MCP capability

logging, prompts, resources, tools

our test · 2026-10-23

Transport

standard input/output, streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

pypi

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

other

package registry · 2026-10-23

Integrity hash

declared (sha256)

package registry · 2026-10-23

Signature / provenance

does not apply

PyPI publishes no registry signature or attestation equivalent to npm dist.signatures

Dependency advisories

none known

OSV.dev · 2026-10-23

Popularity

1,355 downloads a month

package registry · 2026-10-23

Publisher signals

owner: an organization · repository age: 0–30 days · stars: 0–9

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

either (remote or your machine)

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.nimbusbci/nimbus-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.nimbusbci/nimbus-mcp

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.nimbusbci/nimbus-mcp)](https://protocolprobe.com/mcp/servers/io.github.nimbusbci/nimbus-mcp)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology