"Server Fault" matching MCP servers:

Read-only MCP server that surfaces contradictions in an Obsidian vault's knowledge graph via semantic search and reasoning edges.

A Byzantine fault-tolerant MCP Memory server that uses SQLite write-ahead logging and FAISS hybrid vector search for deterministic, secure memory operations.

Provides cross-session persistent memory for coding agents via MCP tools to store, retrieve, and manage notes with hybrid keyword/semantic search and automatic deduplication.

A lightweight MCP server for intelligent, non-invasive analysis of Obsidian vaults.

Enables AI agents to persist, search, and evolve knowledge through a Markdown vault with a typed knowledge graph and MCP interface.

Governed, tamper-evident memory and audit trail for AI agents with 0G Merkle segment sealing. Records agent actions in append-only namespaces with hash chaining, seals segments to 0G Storage, and supports audits and retention enforcement.

Enables agents to store and retrieve hierarchical memory in cryptographically partitioned namespaces, with HMAC-based isolation and Ebbinghaus time-decay so recall fades realistically over time. Runs as a zero-dependency Python STDIO MCP server that returns deterministic JSON results.

Provides persistent OKF memory for DeepSeek Harness by storing and indexing Markdown memories in SQLite FTS5, enabling agents to search, store, and export memories through MCP tools.

Enables AI agents to navigate, search, and rank notes in an Obsidian vault using graph relationships, providing context-aware access to knowledge without exposing raw file contents.

An MCP server that provides semantic search and vault operations for Obsidian notes, enabling agents to recall and manage notes with provenance and low token usage.

Read-only MCP bridge that exposes secure search and fetch tools over an Obsidian-compatible Markdown vault, enabling ChatGPT to query notes without write access.

An MCP server that treats Obsidian vaults as knowledge graphs, enabling AI agents to traverse wikilinks, assemble token-budgeted context, and search with backlink awareness.

Enables MCP-compatible clients to query an Obsidian vault through a local, read-only broker, returning compact, cited context packs with source paths and heading anchors while enforcing a fail-closed sensitivity boundary.

Enables bidirectional sync between a personal Obsidian vault and a shared team vault with configurable rules, change preview, and fast change detection.

A self-hosted memory layer for Claude using plain markdown files, enabling persistent context across different Claude accounts.

Enables AI assistants to search and read a local append-only personal memory vault, retrieve individual events, export context packs, and propose new entries. Proposed writes remain unverified until a human approves them through the CLI.

Enables AI agents to search, read, and safely modify markdown notes in a server-hosted vault over HTTP, with OAuth or machine-token access, atomic writes, conflict checks, dry-run diffs, trash-based deletion, and an audit journal. Also turns YouTube links into transcripts and notes stored in the same vault.

Enables agents to search, read, and write notes in an Obsidian vault, including creating and updating notes in an inbox and syncing changes with Gitea/GitHub.

MCP server that provides a navigable map of an Obsidian vault for coding agents, with tools to outline notes, fetch sections, query frontmatter, and grep content, reducing token usage compared to reading whole notes.

Enables Claude to read, search, and edit your Obsidian notes via a GitHub-synced vault, all hosted for free on Render with no credit card needed.