| FMRS | 55 / 100 · C | 84 / 100 · B | 60 / 100 · C |
|---|
| Reliability | 7 / 20 | 17 / 20 | 9 / 20 |
|---|
| Security and permissions | 9 / 20 | 16 / 20 | 13 / 20 |
|---|
| Maintenance | 12 / 20 | 16 / 20 | 10 / 20 |
|---|
| Documentation | 13 / 20 | 17 / 20 | 15 / 20 |
|---|
| Setup experience | 14 / 20 | 18 / 20 | 13 / 20 |
|---|
| Best for | - Legal-tech teams that need Word Track Changes and existing formatting preserved
- AI-agent workflows operating on local DOCX files
- Developers integrating document processing through the Python or TypeScript SDKs
| - 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 DOCX generation from scratch
- Plain-text editing where Word redlining and XML preservation are unnecessary
- Users seeking Adeu Cloud email-fetching features without connecting to Adeu Cloud
| - 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 | - Read access to user-selected DOCX files
- Write access to save edited or finalized documents
- Windows, Microsoft Word, and the Python backend for live Word integration
- The selected LLM provider may process document text read by the agent
| - 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 | - Broad or ambiguous matches can produce unintended edits; the engine blocks ambiguous matches and invalid structural changes
- AI-generated edits may still conflict with legal or business intent and require human review
- Document contents are processed by the chosen LLM provider, so sensitive files require policy review
- Finalization can change metadata and editing protection, so the target file should be confirmed first
| - 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 Desktop, Gemini CLI, Claude Code, Cursor, Windsurf, VS Code Copilot | 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 | 3 | 6 | 14 |
|---|