Nimbus BCI

Compare Foundation Backbones

foundation.compare

Read-onlyIdempotent

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 skipped. Each backbone embeds your trials frozen (the exact foundation_features preprocessing), a LDA is cross-validated on the embeddings. Returns a PNG image PLUS a JSON text block (and structuredContent.meta.results) with per-backbone accuracy, CI, embed dim, params, and time — pick the foundation_features backbone by measurement, not vibes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>"
    },
    "name": "foundation.compare"
  }
}

Input Schema

Name	Required	Description	Default
`mode`	No	Pack split to load: training \| evaluation \| all (source=dataset).	all
`path`	No	Upload path (source=upload) or absolute local path (source=local).
`source`	Yes	"dataset" (MOABB pack), "upload" (path from data.upload), or "local" (absolute path, local backend only).
`dataset`	No	MOABB dataset id, e.g. "BNCI2014_001" (source=dataset).
`subject`	No	Subject id, e.g. "S01" (source=dataset).

Output Schema

Name	Required	Description
`ok`	Yes
`meta`	No	Figure sidecar. foundation.compare includes results/best/skipped (also as a JSON text content block).
`title`	No
`mimeType`	No
`savedPath`	No	Set when save=true.
`sizeBytes`	No	Set when save=true.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 6, 2026
- addedInput schema / properties / mode / enum
```
Added value: +[
+  "training",
+  "evaluation",
+  "all"
+]
```
- addedInput schema / properties / source / enum
```
Added value: +[
+  "dataset",
+  "upload",
+  "local"
+]
```

Changed1 schema field changedOct 19, 2026

addedOutput schema / properties / meta / description

Added value: +"Figure sidecar. foundation.compare includes results/best/skipped (also as a JSON text content block)."

Changed1 schema field changedOct 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "meta": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "mimeType": {
+      "type": "string"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "savedPath": {
+      "description": "Set when save=true.",
+      "type": "string"
+    },
+    "sizeBytes": {
+      "description": "Set when save=true.",
+      "type": "integer"
+    },
+    "title": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}

AddedOct 14, 2026

TDQS

A3.9/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context on top: the exact pipeline (frozen foundation_features embeddings, cross-validated LDA), the incompatibility policy (backbones that cannot handle the window size or channel count are reported, not silently skipped), and the full output surface (PNG plus JSON text block plus structuredContent.meta.results). That is behavior an agent could not infer from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The operative fact — it benchmarks all backbones and returns ranked metrics — is front-loaded in the first sentence, and the rest adds real detail. The 'YOUR data' capitalisation and the 'not vibes' closing are informal filler that slightly dilutes an otherwise tight definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description does not need to enumerate return fields, yet it does, and it also covers source modes, failure handling, and methodology. The one meaningful omission is cost: running every backbone is potentially long, and there is no hint about expected runtime or whether the caller should poll execution.get instead.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including the source/mode enums is already documented in the schema. The description only alludes to data shape ('window size, channel count') without adding per-parameter meaning, which is the expected baseline when the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: run every available pretrained backbone over the caller's data and rank them, returning a bar chart plus metrics. That is markedly more specific than the surrounding siblings (catalog.leaderboard, execution.run), but it never names or contrasts an alternative tool, so it lands at 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the closing line: use this to choose the foundation_features backbone empirically rather than by guesswork. There is no explicit when-not, no statement about cost/duration, and no pointer to a lighter alternative (execution.run, pipeline.validate) if the caller only wants one backbone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Nimbus BCI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.