zettelbrain (alexcamargos/zettelbrain) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 22 tools. No publisher has claimed this listing.
ZettelBrain e um cofre Zettelkasten em Markdown com um motor Python local para automacao, busca, ingestao e exposicao de ferramentas via Model Context Protocol (MCP).
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
alexcamargos
Source: github_repo_search
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 →
Install from
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.
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.
healthRetrieve server status and system configuration paths.
search_zettelbrainPerform a hybrid (lexical + semantic qmd fallback) search on the ZettelBrain.
retrieval_healthRetrieve operational status for the retrieval engine.
embedding_healthReturn status for the local semantic embedding index.
index_zettelbrain_embeddingsRebuild the local embedding index for Markdown files in the ZettelBrain.
semantic_search_zettelbrainSearch the ZettelBrain through the local semantic embedding index.
suggest_zettelbrain_linksSuggest semantic links for a specific note, excluding existing links.
list_zettelbrain_markdownList all markdown files inside the ZettelBrain folder.
get_semantic_bridgeFind a pair of semantically distant notes in the ZettelBrain to act as a cognitive bridge.
read_zettelbrain_markdownRead the full content of a markdown file in the ZettelBrain.
write_zettelbrain_markdownWrite the UTF-8 content to a markdown file in the ZettelBrain safely.
lint_zettelbrainRun the static audit and validation linter for ZettelBrain.
inspect_pdf_manifestSearch and inspect the PageIndex manifest for a given PDF path.
list_pdf_manifestsList all PageIndex manifests cached in the vault.
read_pdf_cacheRead the PageIndex cache for a document ID, with optional term search.
resolve_pdfResolve a PDF's document ID and verify if its cache exists in PageIndex.
read_pdf_pageRetrieve the text content of a single page from a cached PDF.
persist_pdf_cachePersist a PageIndex tree and its manifest metadata to the cache directory.
index_pdf_cacheRun the configured external PageIndex command and persist its cache output.
compute_pdf_sha256Compute the SHA-256 checksum for a PDF inside raw/papers.
estimate_pdf_processingEstimate the cost, tokens, and time required to process a PDF.
ingest_web_articleIngest a web article from a URL and save it to raw/articles/ as Markdown.
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
22/22 tools missing one or more hints — health (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_zettelbrain (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); retrieval_health (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +19 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.
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.
[](https://m8ven.ai/mcp/alexcamargos/zettelbrain)?variant=verified to the badge URL.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