ObsidianKnowledgeCurator (c-ibarra/ObsidianKnowledgeCurator) is an MCP server listed on the M8ven Trust Index. It scores 47 out of 100, grade D. It declares 25 tools. No publisher has claimed this listing.

Caution

47/100

ObsidianKnowledgeCurator

Item: ObsidianKnowledgeCurator
Rating: 47
Author: M8ven

Autonomous, modular knowledge lifecycle agent built on the Antigravity 2.0 SDK and Model Context Protocol (MCP) for deterministic Obsidian graph curation.

→ c-ibarra/ObsidianKnowledgeCurator · listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

c-ibarra

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Secret credentials may flow to a network call

2 flows detected: GEMINI_API_KEY. We can’t prove the destination matches the brand the credential belongs to.

⚠️

Tool annotations don’t match behaviour

2 read-only tools perform write/delete/exec — ytdlp_get_playlist (line 291: result = subprocess.run(); ytdlp_list_playlist_videos (line 394: result = subprocess.run(cmd, capture_output=True, text=True, timeout=60))

⚠️

Tool descriptions don’t match what handlers do

1 tool describes read intent but its handler mutates — sync_vault_plans (line 200: res = subprocess.run(cmd, capture_output=True, text=True))

🔐

You'll be asked for 3 credentials: GEMINI_API_KEY, GOOGLE_API_KEY, GRAPHIFY_DAEMON_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes25 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

ytdlp_get_transcript

Downloads and returns the transcript (subtitles) of a YouTube video.

ytdlp_get_playlist

Downloads and returns the transcripts of all videos in a YouTube playlist.

ytdlp_list_playlist_videos

Lists the videos of a YouTube playlist without downloading subtitles.

yt_get_transcript

Downloads the transcript (subtitles) of a YouTube video, cleans it and optionally saves it as a .txt file.

yt_list_transcripts

Lists transcripts already saved in ~/Downloads/yt-transcripts/.

sync_multi_choice_deck

Synchronizes a multiple-choice markdown flashcard deck to Anki via AnkiConnect.

sync_basic_deck

Synchronizes a basic/reversed flashcard deck (TSV or Markdown) to Anki via AnkiConnect.

validate_flashcards_deck

Audits a multiple-choice flashcard markdown file against the 6-dimension OKC rubric.

status_flashcards_deck

Inspects card count and Anki sync status for a multiple-choice flashcard deck.

sync_vault_plans

Synchronizes Master Plans and runs the vault health check for a given knowledge base category.

audit_vault_health

Runs the vault health linter to detect dead wikilinks, orphan notes, and contradictions.

find_notes

Searches Obsidian vault notes by title/filename substring (case-insensitive) using SQLite index.

explore_concept

Explores a concept in the knowledge graph, showing its summary/takeaways, source file, and direct relationships.

normalize_notes

Audits, deduplicates, archives stubs, and injects canonical Obsidian headers into notes in a category.

run_doctor_audit

Runs OKC Doctor: comprehensive integrity audit, SQLite DB sync, Master Plans rebuild, ZWSP sanitizer, and Graphify rebuild.

fetch_youtube_data

Fetches YouTube video metadata, downloads/transcribes transcript, and extracts Graphify thematic context.

fetch_article_data

Fetches article web page data with full DOM extraction, concurrent image preservation, and Graphify context mapping.

commit_curated_note

Atomically writes a curated source note to raw/ and concept notes to wiki/, updates the SQLite index, rebuilds Master Plans, and synchronizes the knowledge graph.

fetch_playlist_data

Fetches YouTube playlist structure, video metadata, and full transcripts in batch.

commit_curated_batch

Atomically writes multiple curated raw notes, series master plan, and concept notes to the vault, updates the SQLite index, rebuilds Master Plans, and synchronizes the knowledge graph.

fetch_twitter_data

Fetches Twitter/X post text, metadata, and transcribes embedded video audio via Whisper.

fetch_podcast_data

Fetches podcast or audio link, downloads media, and transcribes with Whisper.

fetch_doc_data

Converts office documents, presentations, PDFs, spreadsheets, and EPUBs to markdown using AnyDoc.

fetch_book_data

Prepares non-fiction book data (PDF, EPUB, DOCX, TXT) using the HDAS ingestion engine.

clean_staging_temp

Safely cleans temporary staging files in temp/ directory.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configMODEL_ENGINE

🔐 secretGEMINI_API_KEY

🔐 secretGOOGLE_API_KEY

configDENSITY_GRADER_PROVIDER

configOLLAMA_HOST

configOLLAMA_MODEL

configMIN_TECHNICAL_SCORE## 1. Technical Density Ingestion Grader ()

configVAULT_ROOTConcurrent Asset Downloads: Uses ThreadPoolExecutor(max_workers=6) to concurrently fetch all article infographics and diagrams directly into <>/assets/images/<slug>-<idx>-<alt_slug>.<ext>.

configOBSIDIAN_VAULT_PATH

configOBSIDIAN_CLI_PATH

configGRAPHIFY_DAEMON_URL

🔐 secretGRAPHIFY_DAEMON_API_KEY

configGRAPHIFY_BACKEND

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployDATABASE_URL

// quality suggestions

Tool annotations

5/25 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

20/25 tools missing one or more hints — sync_multi_choice_deck (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); sync_basic_deck (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); validate_flashcards_deck (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool annotations match behaviour

Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.

Destructive tools are labelled

2 tools perform destructive updates without destructiveHint — yt_get_transcript deletes at line 288 (shutil.rmtree(tmp_dir, ignore_errors=True)); clean_staging_temp deletes at line 904 (item.unlink())

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — sync_vault_plans (line 200: res = subprocess.run(cmd, capture_output=True, text=True))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool description accuracy

sync_vault_plans: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/c-ibarra/obsidianknowledgecurator?variant=verified)](https://m8ven.ai/mcp/c-ibarra/obsidianknowledgecurator)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: c4ae89d50b64d7adb5036aefc643846741a77668

code hash: 56e5e9e5d03815c6a2e17901a3d462cc28feff39686a4af835836ccc65dad39c

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client