Skip to content

note_create MCP tool requires 3 round-trips for agent use: create empty template → read → write content. Add a body parameter (and optional frontmatter fields like tags, series, question, milestone, confidence) so agents can create fully populated notes in a single call, like worklog_note does.

Current flow: 1. note_create(note_type, title) → empty template with placeholder sections 2. Read(path) → see the template (required before Write) 3. Write(path, content) → overwrite with actual content

Proposed: 

note_create(
    note_type="result",
    title="...",
    body="## Result\n\n...",
    tags=["result", "preprocess"],
    series="preprocess_ieeg",
    question=["H1"],
    milestone="ieeg-preprocessing-stable",
    confidence="confirmed",
)

One call, frontmatter fields as named params, body as markdown content below frontmatter. The template scaffolding is useful for manual editing but pure overhead for agents.

Source context: pixecog

PixEcog (pixecog): Neuropixels and ECoG dataset and analysis

Recent commits: 

8dc0d9d Pipeline docs: gitignore docs/pipelines/, relocate hand-authored files
96cd1ec Refactor sharpwaveripple/contracts: extract generic helpers to utils/io, remove pipelines __init__.py
36f9326 Add result note directory and sample note

README:

type: readme

Quick Start for Collaborators

Follow this checklist to get started with Pixecog documentation and workflows.

🐀 Pixecog Project — Compact Overview

Core principles

  • One immutable BIDS raw dataset (raw/) as the canonical baseline
  • Each analysis pipeline ha