A persistent memory layer for Claude Desktop that enables semantic search and CRUD operations on your Obsidian vault using local embeddings and PostgreSQL+pgvector.
Limited view. Automated analysis covers part of this stack. Findings reflect what we verified. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
Limited view: static analysis for this stack is partially covered.
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
celstnblacc
Source: Glama
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
OBSIDIAN_VAULTSTo index multiple vaults, set to a comma-separated list of absolute paths:OBSIDIAN_VAULT"/path/to/your/vault" POSTGRES_PASSWORD=obsidian docker compose up -dOSM_DATA_DIRXDG_DATA_HOMEOSM_PROJECT_ROOTProgramFilesPOSTGRES_HOSTPostgreSQL host localhostPOSTGRES_PORTPostgreSQL port 5432POSTGRES_DBDatabase name obsidian_brainPOSTGRES_USERDatabase user obsidianPOSTGRES_PASSWORDOBSIDIAN_VAULT="/path/to/your/vault" =obsidian docker compose up -dOLLAMA_URLOllama API endpoint http://localhost:11434EMBEDDING_MODELOllama model for embeddings nomic-embed-textDASHBOARD_PORTOBSIDIAN_IGNORE_PATHSComma-separated vault-relative path segments to skip during indexing and watching. Defaults to archive; set it to an empty string to index archived notes. archiveDOCKER_BINOSM_DOCKEROSM_DOCKER_WAITEMBED_TIMEOUTEMBED_WORKERSParallel threads for bulk indexing 4EMBED_BATCH_SIZERERANK_MODELOptional Ollama model for cross-encoder re-ranking (e.g. llama3.2). Disabled when empty. —RERANK_CANDIDATESCandidate pool size fetched before re-ranking 20VAULT_WATCH_POLLINGVAULT_POLL_INTERVALDATABASE_URLTool 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
11/11 tools missing one or more hints — search_vault (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_indexed_notes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); reindex_vault (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 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.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
1 child_process call — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
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/celstnblacc-obsidian-semantic-mcp-lm4rii)?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