What is mne-spectral?

A cautious workflow for measuring frequency-based signal patterns in EEG, MEG, and intracranial EEG data using MNE, a Python neuroscience analysis library.

Computing power spectra, absolute or relative delta-to-gamma band power, spectral slopes, and separating oscillations from 1/f background activity.

It helps prevent misleading conclusions about brain signals by checking study design, band definitions, relative power, and background noise before analysis.

mne-spectral — Skill for Claude Code and Codex by Exekiel179/MNE-MCP

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Exekiel179/MNE-MCP --skill mne-spectral

Clone the repo

git clone --depth 1 https://github.com/Exekiel179/MNE-MCP

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/exekiel179/mne-mcp/mne-spectral/github.svg)](https://agentmods.dev/skills/exekiel179/mne-mcp/mne-spectral)

Your own site

<a href="https://agentmods.dev/skills/exekiel179/mne-mcp/mne-spectral"><img src="https://agentmods.dev/badge/skills/exekiel179/mne-mcp/mne-spectral/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/exekiel179/mne-mcp/mne-spectral"><img src="https://agentmods.dev/badge/skills/exekiel179/mne-mcp/mne-spectral.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,840 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00221	$0.01840
Opus 5.5	$0.00088	$0.00736
Sonnet 5.5	$0.00044	$0.00368
Haiku 4.5	$0.00022	$0.00184

Measured 2mo ago against content hash 6d623a70841b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mne-spectral scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/mne-spectral/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MNE Spectral Analysis (grill → analyze → critic)

Power-spectral analysis of neurophysiology data via the MNE MCP server. This skill is skeptical by design: most spectral mistakes (relative-power compositionality, conflating oscillations with 1/f, asserting normality at small n) run without any error — so the discipline is to grill before computing and critique before believing.

Companion skills: mne-mcp-guard for technical execution safety; mne-methodology-critic for Phase 3. Loaded objects persist in one MNE session.

PHASE 1 — GRILL (before computing anything)

Do not compute a PSD until these are answered. If the user can't answer one, propose a sensible default and explicitly flag the open risk — never silently choose.

Design & claim

What is the hypothesis, and what is the comparison? (group × group, condition × condition, pre × post)
Within- or between-subject? Paired or independent? n per cell?
Confirmatory (hypothesis + ROI/band pre-specified) or exploratory (whole-head, corrected)?

The two questions that decide validity

Absolute or relative power? If relative (band/total): ⚠️ relative bands are compositional (they sum to ~1, are not independent). Per-band t-tests + FDR will be invalid. Plan a log-ratio (CLR/ALR) transform, or use absolute power. (This is the single most common fatal error here.)
Will you separate the 1/f aperiodic component? If not, a difference in spectral slope or total power can masquerade as a band effect. Plan specparam/FOOOF (report exponent/offset + peaks), or justify why raw band power is adequate.

Data & parameters

State: resting (eyes open/closed?) or task-locked? Stationary segment chosen how?
Epoching: length (⇒ frequency resolution ≈ 1/length), overlap, rejection threshold — and its justification. Will the two groups have different rejection rates? (differential rejection fabricates differences)
PSD method: Welch (window, overlap, n_fft) or multitaper (bandwidth)?
Band definitions and edges; align to individual alpha frequency?
Reference, channel selection, units.

Read the full file on GitHub · 136 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/spectral-methods.md 4.7 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 136 lines · 221 tokens per session scan A 6d623a70841b

Subscribe to this mod's changes

mne-spectral is a skill published in the GitHub repository Exekiel179/MNE-MCP (12 stars, last pushed 23d ago), licensed MIT. It adds 221 tokens to every session and 1,840 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Scientific

mne-spectral next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mne-spectralExekiel179/MNE-MCP	Skill	12	23d ago	MIT	A	221	Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code