"obsidian" matching MCP servers:

Enables multiple AI agents to share a single Obsidian vault through streamable HTTP, with per-agent bearer tokens whose folder-level read/write permissions are enforced server-side so denied folders stay invisible. Offers tools for listing, reading, searching, stating, writing, editing, appending, moving and optionally trashing notes, backed by revision checks, atomic writes, per-file locking and an audit log.

A Model Context Protocol server that gives AI agents bounded, auditable access to propose changes to an Obsidian vault stored in GitHub, with per-agent expiring tokens, read/write/deny path policies, mutability rules, frontmatter checks, and human-reviewed proposal branches.

Enables local network discovery and security scanning to identify connected devices, manufacturers, and potential risks. It allows users to track network changes and export inventories into Markdown or Obsidian-compatible formats.

Enables AI agents to securely use secrets from an Obsidian vault by injecting them into command environments without exposing the values, with auditing and approval controls.

An MCP gateway that enforces step-up authentication using WebAuthn passkeys for remote clients, requiring session handles for read operations and fresh passkey confirmations for writes to protect an Obsidian vault.

A security-hardened MCP server that enables AI models to safely interact with Obsidian vaults through sandboxed file operations and todo tracking. It implements strict validation layers and resource limits to protect the local filesystem from potentially hostile tool calls.

Enables agents to query and append shared memory in a local, user-owned Markdown/Obsidian vault through hybrid vector and keyword retrieval with reranking, while redacting secrets and PII into sanitized, minimum-viable briefs. It also dispatches approved tasks to Wajo Fo's MCP endpoint over StreamableHTTP or SSE and writes execution receipts back to the vault.