| FMRS | 63 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 8 / 20 | 12 / 20 |
|---|
| Security and permissions | 12 / 20 | 18 / 20 |
|---|
| Maintenance | 13 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 |
|---|
| Setup experience | 14 / 20 | 15 / 20 |
|---|
| Best for | - Developers already on Appwrite Cloud who want AI-assisted backend administration
- Teams that prefer browser-authenticated OAuth scopes over managing API keys
- Self-hosted Appwrite operators who can run a local stdio bridge with a project API key
| - 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 without an Appwrite project or account
- Clients that lack remote MCP/OAuth support and cannot install Node.js for the mcp-remote bridge
- Non-Appwrite backend workflows
| - 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 | - OAuth scopes approved during the browser consent flow (covering databases, users, functions, teams, storage, etc.)
- For self-hosted use, an Appwrite project API key with permissions matching the operations invoked
| - 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 backend access (databases, users, functions, storage) if overly broad OAuth scopes or an overly permissive API key are granted
- Destructive operations (deleting data, modifying users/teams) are possible if the AI client is given write scopes
- The hosted server is a third-party (Appwrite-operated) service brokering requests to your Appwrite project
| - 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, Claude Desktop, Cursor, VS Code, Codex, OpenCode, Windsurf, Gemini CLI, Antigravity, GitHub Copilot CLI, Zed, Warp, JetBrains AI Assistant / Junie, Cline | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 1 | 0 |
|---|