| FMRS | 62 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 8 / 20 | 12 / 20 |
|---|
| Security and permissions | 13 / 20 | 18 / 20 |
|---|
| Maintenance | 14 / 20 | 16 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 12 / 20 | 15 / 20 |
|---|
| Best for | - Obsidian users who want an AI coding-agent chat and inline editor built into their vault
- Developers already using Claude Code, Codex, or similar CLIs who want vault-aware access to them
- Note-takers who want agent-assisted file read/write, search, and multi-step workflows scoped to their vault
| - Engineering teams scaling AI coding agents while controlling spend
- Platform teams that need auditable, rollback-aware agent execution records
- Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
|
|---|
| Not for | - Users looking for a standalone MCP server to add tools/resources to an MCP client — Claudian is a client/host, not an MCP server
- Mobile Obsidian users — the plugin is desktop only (macOS, Linux, Windows)
- Users without any supported CLI harness (Claude Code, Codex, Grok Build, OpenCode, or Pi) installed and a compatible API/subscription provider
| - Developers who just want a simple code-completion helper without run governance
- Teams unwilling to accept local JSONL run records with HMAC signing
- Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
|
|---|
| Required permissions | - Read/write/edit access to files within the Obsidian vault (the agent's working directory)
- Bash/shell command execution via the underlying CLI harness
- Network access to the selected AI provider (Anthropic, OpenAI, xAI, or OpenCode/Pi providers) and to any configured MCP server endpoints
| - Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
- Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
- Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
- Execution of user-configured verifier commands (e.g. npm test)
|
|---|
| Risks and side effects | - Broad file read/write and bash access to the vault means a misbehaving or misprompted agent could modify or delete notes
- Input, attached files, images, and tool outputs are sent to the selected third-party API provider, so sensitive vault content could leave the local machine
- MCP servers configured within the plugin are additional third-party endpoints whose trustworthiness is outside Claudian's control
| - Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
- Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
- Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
- Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
|
|---|
| Supported clients | | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 0 | 0 |
|---|