| FMRS | 32 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 4 / 20 | 12 / 20 |
|---|
| Security and permissions | 5 / 20 | 18 / 20 |
|---|
| Maintenance | 10 / 20 | 16 / 20 |
|---|
| Documentation | 5 / 20 | 18 / 20 |
|---|
| Setup experience | 8 / 20 | 15 / 20 |
|---|
| Best for | - Developers building SceneView 3D/AR apps (Android, iOS, Web) who already use or want to adopt Rerun.io for debugging.
- Teams that need replayable AR session evidence for bug reports and post-mortem analysis.
- Debugging scenarios that combine SceneView AR poses, planes, and cloud anchors with Rerun's timeline visualization.
| - 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 | - Projects not using SceneView or Rerun.
- End users of a released application (this is a debugging tool, not a user-facing feature).
- Teams that require an officially maintained Rerun.io MCP server and do not accept a community-maintained implementation.
| - 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 | - No dedicated permission list is published in the source material.
- Based on the described features, the server may fetch and execute the npm package and its dependencies via npx.
- It may launch local Python sidecar processes (Rerun SDK).
- It may write local .rrd recording files and may start or interact with a local web viewer instance.
| - 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 | - The server is community-maintained by SceneView, not by Rerun.io, so standard supply-chain and local-execution risks apply.
- The npm package and its dependencies may introduce third-party code; pin the version and review the published package before relying on it.
- The server may process AR session data, so avoid using it with sensitive data in unfamiliar environments.
- If Python sidecar dependencies are missing, features may fail, and errors may only appear in client logs.
| - 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 Desktop, Claude Code, Cursor, Windsurf | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 0 | 0 |
|---|