| FMRS | 61 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 9 / 20 | 12 / 20 |
|---|
| Security and permissions | 9 / 20 | 18 / 20 |
|---|
| Maintenance | 14 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Developers already using the Salesforce CLI and a DX project
- Teams that want an AI coding assistant to operate directly on Salesforce metadata, Apex, and LWC
- Projects migrating Aura to LWC or adopting DevOps Center workflows
| - 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 a local Salesforce CLI setup or any authorized org
- Cases needing only trivial read-only lookups without wanting the context overhead of the broader toolset (can be trimmed via --toolsets, but the default footprint is still sizable)
| - 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 | - Requires orgs to be pre-authorized locally via `sf org login web` or equivalent
- Access is scoped per `--orgs`: specific orgs, the default org/Dev Hub, or (use with caution) all authorized orgs
- Several tools have write access — deploying/retrieving metadata, creating or deleting scratch orgs, assigning permission sets, committing DevOps Center work items
| - 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 | - `ALLOW_ALL_ORGS` grants the server access to every locally authorized org, which can expose production orgs if misconfigured
- Tools like `deploy_metadata` and `delete_org` make real changes or deletions to orgs — misuse carries data/config risk
- Telemetry is enabled by default; use `--no-telemetry` explicitly if privacy/compliance requires disabling it
- `DEFAULT_TARGET_ORG`/`DEFAULT_TARGET_DEV_HUB` resolve dynamically on every tool call, so switching your local default org changes which org the server can act on
| - 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, GitHub Copilot, Cline, Cursor, Trae, Windsurf, Zed | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 89 | 0 |
|---|