Skip to content
Agentmart
Submit a tool

VibeDNA Journal

One journal file per project that your AI reads at session start and updates as it works.

Connector by marstudio360 · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Chalk Labs

Need help deploying VibeDNA Journal?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Desktop. Read the repository before you give any tool access to your data.

Download the bundle

MCP bundle (.mcpb): open it with Claude Desktop.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

One journal file per project that your AI reads at session start and updates as it works.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
14 read · 6 write · 0 delete · 5 not yet classified
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Downloaded binary

Tools by what they do 25

Read from the source code; the running server may list different tools.

Read 14 · Look things up without changing anything.

  • check_for_update
  • journal_browse
  • journal_get
  • journal_get_claude_rule
  • journal_library
  • journal_list
  • journal_list_sections
  • journal_market
  • journal_overlap_check
  • journal_read
  • journal_read_section
  • journal_search
Show 2 more tools
  • journal_stats
  • vibedna_info

Write 6 · Create, change, send or run things.

  • journal_append
  • journal_backup_to_drive
  • journal_config_add_root
  • journal_create
  • journal_install_rule
  • journal_update_section

Not yet classified 5 · We could not tell from the name and description.

  • journal_handoff_brief
  • journal_index_refresh
  • journal_market_index
  • journal_pair
  • journal_recent_changes

Network hosts it talks to 1

  • github.com · found in install command

Files it touches

  • Any path the agent passes to its tools

Tools (25)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • check_for_update

    Is this copy behind the published version? Your copy is a folder on your machine, so it stays exactly as it was the day you installed it while fixes keep shipping. This asks what is published now and tells you whether to update, and how. It sends nothing about you: just a version number comes back.

  • journal_append

    Append a timestamped entry to a journal. Most common operation. name_or_path: which journal (short name or path) entry: markdown content of the new entry tag: optional tag prefix (e.g. 'fix', 'incident', 'feature', 'decision') section_header: if set, wraps the entry under '## <section_header>' (creates section if not present) Format appended: ## <timestamp> [<tag>] <first-line-of-entry> <entry> ---

  • journal_backup_to_drive

    Upload journal(s) to Google Drive via rclone. name_or_path: which journal (empty = ALL indexed journals) remote: rclone remote name (default 'gdrive', must be configured: `rclone config create gdrive drive`) remote_folder: subfolder on the remote (default 'Journals') Each journal uploads to <remote>:<remote_folder>/<project>/<name>. Requires rclone installed + 'gdrive' (or your chosen remote) configured.

  • journal_browse

    Structured browse of the library by product metadata (for the marketplace). domain / tier / kind: filters (kind = raw | refined | skill) tag: substring match against the tags field Returns journals with their product metadata (title, domain, tier, tools, tags, description).

  • journal_config_add_root

    Add a root directory to scan (writes to ~/.journal/config.toml).

  • journal_create

    Create a new project journal. ONE journal per project = single source of truth. name: filename (e.g. 'CRYPTOMIND_JOURNAL.md'). Auto-appends .md if missing, auto-uppercases convention. project_dir: absolute path to the folder where it should live (usually the project root) body: initial markdown (optional, defaults to a scaffold with all standard sections) Default scaffold includes sections: Vision · Current state · Roadmap · Decisions log · Incidents · Handoff for next session · Recent entries.

  • journal_get

    Get a journal by slug. If you own it (paired) it writes the .md into dest_dir (default ~/.journal/library). If you do NOT own it, returns {price, checkout_url}: show the user; if they agree, they pay on vibedna.ai. Pass confirm=True to also open the checkout in the browser. After paying, call journal_get again to install. The engine never takes payment.

  • journal_get_claude_rule

    Return the recommended CLAUDE.md rule that makes Claude AUTO-MAINTAIN your journals: read at session start, append after every shipped piece of work, update state/roadmap/handoff sections as things change. Without this rule, Journal MCP tools sit unused. WITH this rule, every Claude session opens cold, reads the project journal, and is up to speed in 30 seconds, no re-explaining. Paste this into your `~/.claude/CLAUDE.md` (global) OR a project's `CLAUDE.md` (per-project). Or use `journal_install_rule()` to do it automatically.

  • journal_handoff_brief

    Render a journal as a concise handoff brief for a new session to read. Pulls: file header + most recent N entries (separated by --- dividers). name_or_path: which journal max_lines: total line cap of the brief (default 50)

  • journal_index_refresh

    Rescan all configured roots, refresh the journal index. Run this when you've created new journals or want fresh state. Returns: roots scanned, journals found, DB path.

  • journal_install_rule

    Install the Journal CLAUDE.md rule so Claude actually USES the journals. scope: "global" → appends to `~/.claude/CLAUDE.md` (applies to all sessions on this machine) "project" → appends to `./CLAUDE.md` in current working directory (per-project) confirm: must be True to actually write. Default False = preview only. The rule is idempotent: if it's already in the file, this is a no-op. Returns: what would be (or was) written and where.

  • journal_library

    List every journal the paired user owns, each with a ready download. Re-install free on any machine. Requires pairing (journal_pair). Mirrors your vibedna.ai library.

  • journal_list

    List journals in the library. project: substring filter on project folder name (e.g. 'MYAPP', '') last_days: only journals modified in last N days (0 = all) limit: max results Auto-refreshes index if it's empty.

  • journal_list_sections

    List the H2 sections of a journal so you know where to append.

  • journal_market

    Browse the live VibeDNA journal shelf (vibedna.ai). Returns each journal with its price and a checkout link. No pairing needed to browse. Filter by free-text query (title/description/tools/tags) or domain (web, creative-tools, publishing, audio-tools).

Show 10 more tools
  • journal_market_index

    The marketplace feed: every product of a kind (default 'refined') with full metadata, for a Catalog API or storefront to consume. Commerce fields (price, payouts) live in the Catalog layer, not here. This is content + metadata only.

  • journal_overlap_check

    Dedup helper: find other journals that overlap this one, by shared H2 section headings and shared significant terms. Use before pricing to catch two journals that teach the same skill (the Refinery dedup step).

  • journal_pair

    Pair this install to a VibeDNA account so you can browse, buy, and re-download journals from the chat. Get the connect-token from vibedna.ai/library ("Connect your AI"), then call journal_pair(token="vbd_conn_..."). Idempotent: with no token it reports the current pairing. The engine never takes payment.

  • journal_read

    Read a journal's full contents. name_or_path: full path OR short name (fuzzy). E.g. "MYAPP", "MYAPP_JOURNAL.md", "myapp\MYAPP_JOURNAL.md" max_kb: if > 0, cap response at this many KB (returns tail). 0 = full file. Returns the raw markdown.

  • journal_read_section

    Read just one section of a journal by name (case-insensitive substring match). Returns the content between '## <section>' and the next '##'.

  • journal_recent_changes

    What journals have been updated lately. Use to see cross-session activity: 'What did the FLASHARB tab journal in the last 12h?'

  • journal_search

    Full-text search across journal contents, ranked best-first (FTS5 + bm25). query: words or a phrase to find inside the markdown project: filter by project substring kind: filter by kind (raw | refined | skill), empty = all limit: max results Returns matched journals ranked by relevance, each with a context snippet.

  • journal_stats

    Library snapshot: total journals, by project, biggest, freshest.

  • journal_update_section

    Update a specific section of the journal. section: section title (case-insensitive substring match, e.g. 'roadmap', 'current state') new_content: the new section body (without the '## ...' header, that's preserved) mode: 'replace' (default, rewrites the section body) | 'append' (adds new_content to the end of the section) | 'prepend' (inserts new_content at the top of the section body) Use for: keeping Current state / Roadmap fresh, logging Decisions, recording Incidents.

  • vibedna_info

    Product info.

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Oct 6, 2026 (24 days ago)
Last release
Oct 6, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.marstudio360/vibedna-journal-mcp
Version
1.0.3
Auth
No auth
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from marstudio360

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get VibeDNA Journal running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying VibeDNA Journal?

CallGet help
Cite this page

VibeDNA Journal MCP server. Agent Mart. https://agentmart.dev/connectors/marstudio360-vibedna-journal-mcp (last updated 2026-10-24)