| FMRS | 63 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 10 / 20 | 12 / 20 |
|---|
| Security and permissions | 12 / 20 | 18 / 20 |
|---|
| Maintenance | 12 / 20 | 16 / 20 |
|---|
| Documentation | 14 / 20 | 18 / 20 |
|---|
| Setup experience | 15 / 20 | 15 / 20 |
|---|
| Best for | - Front-end developers on Next.js 16+ who want coding agents to read live dev server state directly
- Teams using MCP-capable agent workflows such as Claude Code, Cursor, or Codex
- Next.js projects that need version-accurate docs instead of fetching docs over the network
| - 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 Next.js or below version 16 (nextjs_index / nextjs_call need a running Next.js 16+ dev server)
- Users expecting the server to fetch docs itself or drive the browser directly (nextjs_docs and browser_eval are gateways only)
- Deployments needing non-stdio transports such as remote HTTP
| - 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 the project's next/package.json locally to resolve the installed Next.js version and docs path
- Network access to local dev server ports (e.g. localhost:3000) to discover and call the /_next/mcp endpoint
- Write local files under ~/.next-devtools-mcp/ (telemetry-id, telemetry-salt, and debug log mcp.log)
- browser_eval may prompt installation of a global CLI: npm install -g agent-browser
| - 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 | - Anonymous usage telemetry is collected by default (tool usage, anonymous error messages, session ID, timestamps, and basic environment such as OS and Node.js version); your code, file contents or paths, personal data, credentials, and tool arguments are not collected. Opt out with export NEXT_TELEMETRY_DISABLED=1, and delete local telemetry data with rm -rf ~/.next-devtools-mcp.
- Upstream requests for runtime tool calls, including response-body reads, have a 60-second deadline.
- nextjs_docs falls back to https://nextjs.org/docs when an installed release has no bundled docs and asks the agent to verify APIs against the installed version.
- Using next-devtools-mcp@latest keeps clients on the latest version, which may introduce unexpected changes.
| - 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, Cursor, Codex, Amp, Gemini, Antigravity, VS Code, Warp | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 4 | 0 |
|---|