Nimbus BCI
REMOTE · NIMBUS-MCP.FLY.DEV · 2 COMPONENTS
AI agents build, train, and analyze BCI/EEG pipelines: data, models, experiments, live sessions.
Available components
Last scanned (11 hours ago)
Scores higher than 23% of remote servers
Reachable. Last reached 24 Oct 2026.
Category Health and Science
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security89
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability0
- Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http. See how to fix → View diagnostics → Unverified
Schema Quality & AI Usability0
- Schema blocked by authentication: the endpoint requires auth we don't have to read it. See how to fix → Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Tool Safety0
- Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Capabilities0
- Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. See how to fix → Unverified
Unverified: 6 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm. Claim this server and supply a read-only token to verify it and lift the score.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Oct 26 −34
- Endpoint reachability: reachable → behind authorisation ▼ security
- Transport: pass → unverified ▼ security
- Stability: fail → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Authorization: fail → pass ▲ security
- First check of Authorization: partial security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- First check of Schema quality: unverified functional
- 20 Oct 26 0
- Stability: 0.47 → fail ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- New tool “data.delete_upload”, which the server declares destructive security
- Tool “stats.grouped” rewrote its description, which is the text the model reads security
- Tool “project.save” rewrote its description, which is the text the model reads security
- Tool “leaderboard.submit” rewrote its description, which is the text the model reads security
- Tool “foundation.compare” rewrote its description, which is the text the model reads security
- Tool “experiment.run” rewrote its description, which is the text the model reads security
- Tool “experiment.get” rewrote its description, which is the text the model reads security
- Tool “data.upload” rewrote its description, which is the text the model reads security
- Tool “account.whoami” rewrote its description, which is the text the model reads security
- “project.save” added a required parameter “expected_revision”, so existing callers break ▼ functional
- Server version: 0.14.11 → 0.14.12 functional
- Server version: 0.14.4 → 0.14.11 functional
- “leaderboard.submit” added an optional parameter “verification” cosmetic
- “stats.grouped” reworded the description of “execution_ids” cosmetic
- 18 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- New tool “project.delete”, which the server declares destructive security
- Tool “stats.grouped” rewrote its description, which is the text the model reads security
- Tool “pipeline.validate_node” rewrote its description, which is the text the model reads security
- Tool “execution.run” rewrote its description, which is the text the model reads security
- Tool “catalog.leaderboard” rewrote its description, which is the text the model reads security
- Tool “calibration.train” rewrote its description, which is the text the model reads security
- Destructive annotations: pass → 100 functional
- Server version: 0.14.2 → 0.14.4 functional
- “pipeline.validate_node” added an optional parameter “dataset” cosmetic
- “catalog.leaderboard” added an optional parameter “dataset_id” cosmetic
- “pipeline.validate_node” reworded the description of “node_type” cosmetic
- “stats.grouped” reworded the description of “execution_ids” cosmetic
- “plots.confusion” reworded the description of “matrix” cosmetic
- “leaderboard.submit” reworded the description of “dataset_id” cosmetic
- “leaderboard.submit” reworded the description of “code” cosmetic
- “calibration.train” reworded the description of “paradigm” cosmetic
- “calibration.train” reworded the description of “template_id” cosmetic
- “protocol.start_assignment” dropped the optional parameter “name” cosmetic
- “protocol.save” dropped the optional parameter “name” cosmetic
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “protocol.export_stats” rewrote its description, which is the text the model reads security
- Schema quality: 6787 → 8080 ▼ functional
- Schema quality: 6787 → 8062 ▼ functional
- Tool coverage: 90% → 100% ▲ functional
- Tool “plots.leaderboard” now declares an output schema ▲ functional
- Tool “plots.erp” now declares an output schema ▲ functional
- Tool “plots.dataset” now declares an output schema ▲ functional
- Tool “plots.confusion” now declares an output schema ▲ functional
- Tool “foundation.compare” now declares an output schema ▲ functional
- Server version: 0.14.1 → 0.14.2 functional
- Server version: 0.14.0 → 0.14.1 functional
- Server version: 0.13.2 → 0.14.0 functional
- New tool “protocol.export_stats” functional
- New tool “protocol.stop” functional
- New tool “protocol.start_assignment” functional
- New tool “protocol.session_status” functional
- New tool “protocol.save” functional
- New tool “protocol.validate” functional
- New tool “protocol.resume” functional
- New tool “protocol.list” functional
- New tool “protocol.pause” functional
- “leaderboard.submit” added an optional parameter “backbone_revision” cosmetic
- “leaderboard.submit” added an optional parameter “backbone_repo” cosmetic
- “leaderboard.submit” added an optional parameter “backbone_license” cosmetic
- “leaderboard.submit” added an optional parameter “backbone_kind” cosmetic
- “leaderboard.submit” reworded the description of “code” cosmetic
- “leaderboard.submit” made “code” optional cosmetic
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “catalog.leaderboard” rewrote its description, which is the text the model reads security
- Server version: 0.13.1 → 0.13.2 functional
- Server version: 0.13.0 → 0.13.1 functional
- New tool “foundation.compare” functional
- 13 Oct 26 0
- Tool “leaderboard.submit” rewrote its description, which is the text the model reads security
- Tool “plots.leaderboard” rewrote its description, which is the text the model reads security
- Server version: 0.12.1 → 0.13.0 functional
- “leaderboard.submit” added an optional parameter “track” cosmetic
- “plots.leaderboard” reworded the description of “track” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 24 Oct 2026 · Probed https://nimbus-mcp.fly.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=*.fly.dev | CN=YE1,O=Let's Encrypt,C=US | 20 Oct 2026 | 18 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 5e6e25e6df778e81cd07b85fc9f12d4df7d |
| SANs: *.fly.dev | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of nimbus-mcp.fly.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| fly.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On connection |
| HTTP status | 401 |
WWW-Authenticate challenge Bearer resource_metadata="https://nimbus-mcp.fly.dev/.well-known/oauth-protected-resource/mcp"
Bearer resource_metadata="https://nimbus-mcp.fly.dev/.well-known/oauth-protected-resource/mcp"| Header | Value |
|---|---|
| www-authenticate | Bearer resource_metadata="https://nimbus-mcp.fly.dev/.well-known/oauth-protected-resource/mcp" |
Protected resource metadata
| Document | https://nimbus-mcp.fly.dev/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://nimbus-mcp.fly.dev/mcp |
| Authorisation server | https://nimbus-mcp.fly.dev/ |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://nimbus-mcp.fly.dev/mcp | Auth required | 401 | |
| http (plaintext) | http://nimbus-mcp.fly.dev/mcp | HTTPS enforced | 301 | https://nimbus-mcp.fly.dev/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
protocol.session_status Protocol.Session Status ~84
Live snapshot of a protocol deploy session: the scheduler block / session progress + threshold state (under ``protocol``) beside the telemetry window (recent indicators, quality, stats).
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The deploy session to inspect (from start_assignment). |
| window | integer | – | How many recent predictions to include (1-200, default 50). |
Structured output declared, but exposes no named fields.
No examples provided.
protocol.start_assignment Protocol.Start Assignment ~381
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 an active-arm session and data.upload-ing its recording), then persists the protocol graph as a deployable execution. Requires a Pro plan for LIVE hardware sessions; simulated-source sessions (the default template) are free. Graph source: execution_id reuses THAT run's stored graph (it must contain a protocol_session node; no device is pre-connected — the deploy session's data source stays yours). Without execution_id the built-in template graph is cloned — simulated source → bandpass → bandpower_indicator → protocol_session stamped with the protocol refs — and a simulated device is connected to the returned session id. The session starts when a client opens {statusUrl} (the deploy WS), sends init_deployment with modelExecutionId={executionId}, then start; the Studio app shows the feedback panel automatically. Poll protocol.session_status; stop with protocol.stop (the recording's block annotations + assignment progression are written on stop).
| Name | Type | Req | Description |
|---|---|---|---|
| arm | string | yes | active | sham. |
| confirm | boolean | – | MUST be true — explicit go-ahead for a session on a human. |
| execution_id | – | – | Optional completed execution whose stored graph carries a protocol_session node; default clones the template. |
| protocol_id | string | yes | Saved protocol id (protocol.save). |
| protocol_version | integer | yes | Immutable version the assignment pins. |
| subject_label | string | yes | Subject identifier (e.g. "S01"). |
| yoked_donor_upload_id | – | – | Donor recording upload (required when the arm's blocks resolve to yoked — the backend validates coverage). |
Structured output declared, but exposes no named fields.
No examples provided.
protocol.stop Protocol.Stop ~74
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 reported, never raised).
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The deploy session to stop. |
Structured output declared, but exposes no named fields.
No examples provided.
protocol.validate Protocol.Validate ~116
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 exception.
| Name | Type | Req | Description |
|---|---|---|---|
| spec | object | yes | Wire-format protocol document (camelCase): id, name, indicator {name, transform}, armDefaults, blocks [{id, kind: assessment|training, durationSec, feedback?}], threshold, sessions, breakCriteria. |
Structured output declared, but exposes no named fields.
No examples provided.
python.validate Python.Validate ~141
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 the code, so it is safe against the hosted backend. Use it before execution.run to catch syntax errors, missing methods, or the wrong class name cheaply.
| Name | Type | Req | Description |
|---|---|---|---|
| class_name | – | – | Contract class to instantiate; omit to auto-detect the first class defining fit+predict. |
| code | string | yes | Python source of the model class (<=256KB UTF-8). |
Structured output declared, but exposes no named fields.
No examples provided.
stats.grouped Stats.Grouped ~353
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 CV over >= 3 subjects. Session groups within one subject (multi-session single-subject runs) are refused with ``nimbus.stats.non_subject_groups`` — those are not independent subjects. A plain single-subject CV run with no subject/session grouping stores no group stats and fails with ``nimbus.stats.insufficient_groups``. What it does: pools the per-subject accuracies each run's evaluation plan stored, then reports the between-group summary — mean accuracy with a t-interval and a one-sample t-test vs chance. Responses label ``groupKind``, real ``groupKeys`` (subject ids like S01 when stamped or recoverable), ``perGroup`` (key + accuracy pairs), ``overall.pooledExecutionIds``, and ``kindBreakdown`` / ``overall.kindBreakdown`` (per_subject vs loso etc. with n + mean — #470; between-group pooled mean is unchanged).
| Name | Type | Req | Description |
|---|---|---|---|
| chance | – | – | Chance level in [0, 1]; default 1/nClasses per execution. |
| execution_ids | array | yes | 1–25 executions (from execution.run) to pool. Runs without subject group stats are reported with nulls but do not fail the request — unless NONE qualifies (``nimbus.stats.insufficient_groups``) or on… |
Structured output declared, but exposes no named fields.
No examples provided.
stream.start Stream.Start ~331
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_sec (default 900), the session is stopped and the device disconnected automatically — an abandoned stream never keeps running on the user's head. Any poll resets the timer; idle_timeout_sec=0 disables the watchdog.
| Name | Type | Req | Description |
|---|---|---|---|
| chunk_size | integer | – | Samples per streamed chunk (default 125). |
| confirm | boolean | – | MUST be true to start — the explicit user go-ahead for a live session on their head; anything else is refused with zero requests. |
| connection_type | – | – | Device-specific selector (e.g. serial vs wifi). |
| device_type | string | yes | Device id from device.list (e.g. "brainbit"). |
| idle_timeout_sec | integer | – | Watchdog: stop+disconnect after this many seconds without a status poll (default 900; 0 disables). |
| ip_address | – | – | Device IP for network/wifi devices. |
| ip_port | – | – | Port for network devices. |
| mac_address | – | – | Bluetooth MAC (BT devices). |
| n_channels | integer | – | Channel count to open (default 8). |
| port | – | – | Serial/COM port for wired devices. |
| serial_number | – | – | Device serial (some BLE stacks). |
| session_id | – | – | Optional existing session to resume/reuse. |
| source_id | – | – | LSL source id. |
| stream_name | – | – | LSL stream name (LSL devices). |
Structured output declared, but exposes no named fields.
No examples provided.
stream.status Stream.Status ~59
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).
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The streaming session to inspect. |
Structured output declared, but exposes no named fields.
No examples provided.
stream.stop Stream.Stop ~53
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The streaming session to stop. |
Structured output declared, but exposes no named fields.
No examples provided.
stream.telemetry Stream.Telemetry ~197
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: modelless hardware streams (no classifier) report live signal quality + focus/relaxation band-power indicators with latestPrediction null; deployed sessions additionally carry predictions and confidence stats. Expect low confidence during filter/ASR warm-up (first seconds); quality < 0.5 or high artifactProbability means the signal is poor. 404 => session not active in this backend. Each poll also feeds the idle watchdog (see stream.start's idle_timeout_sec), keeping an actively watched session alive.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The streaming session to read telemetry for. |
| window | integer | – | How many recent predictions/chunks to include (default 50). |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the Nimbus BCI MCP server?
Nimbus BCI is a hosted endpoint at https://nimbus-mcp.fly.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · nimbus-mcp.fly.dev
claude mcp add --transport http nimbusbci-nimbus-mcp 'https://nimbus-mcp.fly.dev/mcp'
What is the Nimbus BCI MCP server?
Nimbus BCI is an MCP server listed in the public MCP registry as io.github.nimbusbci/nimbus-mcp. AI agents build, train, and analyze BCI/EEG pipelines: data, models, experiments, live sessions. This page covers its hosted endpoint (https://nimbus-mcp.fly.dev/mcp).
Is the Nimbus BCI MCP server safe to use?
Nimbus BCI scores 36 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Nimbus BCI MCP server expose?
Nimbus BCI exposes 60 tools: account.whoami, catalog.nodes, catalog.node_schema, catalog.templates, catalog.template, and 55 more. Their descriptions and schemas cost roughly 8,291 tokens of context every time the server is loaded.
Does the Nimbus BCI MCP server require authentication?
Yes. Nimbus BCI asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Nimbus BCI MCP server still maintained?
Nimbus BCI is still listed as active in the MCP registry. We last reached this channel on 24 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.