| FMRS | 47 / 100 · D | 84 / 100 · B | 60 / 100 · C |
|---|
| Reliability | 6 / 20 | 17 / 20 | 9 / 20 |
|---|
| Security and permissions | 8 / 20 | 16 / 20 | 13 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 | 10 / 20 |
|---|
| Documentation | 12 / 20 | 17 / 20 | 15 / 20 |
|---|
| Setup experience | 11 / 20 | 18 / 20 | 13 / 20 |
|---|
| Best for | - AI agent developers who already use bash and want one filesystem interface instead of many SDKs/MCPs
- Workflows that need to pipe data between S3, Google Drive, Slack, OneDrive/SharePoint, and similar backends
- Teams embedding an agent workspace directly inside a Python/TypeScript app (FastAPI, Express, etc.)
| - Local assistants that need to work inside explicitly approved directories
- Individuals and development teams that want path-based data boundaries
| - Users who want to access a local Obsidian vault through multiple MCP clients.
- Note workflows that need to preserve raw formatting for unmodified frontmatter fields.
- Knowledge-base users who need local file operations, search, and tag management.
|
|---|
| Not for | - Simple single-service use cases that don't need a unified cross-backend interface
- Non-macOS/Linux environments where FUSE-based mounts aren't supported
- High-security scenarios requiring fine-grained, per-action permission control rather than a general bash execution interface
| - Highly sensitive environments that cannot allow model access to local file contents
- Shared remote file-service use cases
| - Users without an Obsidian vault or local vault directory.
- Users seeking a remote network service, cloud-hosted service, or non-MCP integration.
- Users who do not want an AI assistant to access or modify vault content and structure.
|
|---|
| Required permissions | - Access credentials or API tokens for each mounted backend (e.g., OneDrive, SharePoint, S3, Slack, Gmail)
- Local filesystem read/write access (for RAM/Disk resources and caching)
- Outbound network access to reach remote backend APIs
| - Read access to every local directory listed in the configuration
- Filesystem write access when write or move tools are enabled
| - Requires Node.js 18 or later.
- Requires read access to the specified vault; writing, moving, and deleting also require the corresponding write permissions.
- The server can access allowed `.md`, `.markdown`, `.txt`, `.base`, and `.canvas` files.
- The AI assistant can see allowed file content, directory structure, and some file metadata.
|
|---|
| Risks and side effects | - A single bash-like execution interface can let an agent broadly read, copy, or overwrite data across every mounted, potentially sensitive backend
- Content pulled in from mounted sources (e.g., Slack messages, email) carries prompt-injection risk that could influence subsequent agent behavior
- Index and file caches (default TTL 10 minutes / default 512MB) can serve stale data until they expire
- Once credentials are configured for a workspace, an agent may end up with broader cross-service access than intended for a given task
| - Sensitive files inside an allowed directory may enter model context
- Write and move tools change real files; keep scopes narrow and maintain backups
| - The server provides full read/write access within its security boundaries, so incorrect instructions can modify or delete notes.
- Vault content, structure, and file metadata may be exposed to AI conversations with access.
- Permanent deletion may be unrecoverable; back up the vault before write operations.
- Path filtering does not isolate content, so sensitive data in allowed files remains readable.
|
|---|
| Supported clients | Claude Code | Claude Desktop, Cursor, Cline, Windsurf | Claude Desktop, Claude Code, OpenCode, Goose Desktop, ChatGPT Desktop, IntelliJ IDEA 2025.1+, Cursor IDE, Windsurf IDE, Ontheia, Microsoft Copilot Studio, OpenAI Codex |
|---|
| Tools | 1 | 6 | 14 |
|---|