Second Opinion MCP
About
Consult multiple AI models, including local, cloud, and enterprise services, to get diverse perspectives on a topic.
Details
- Author
- procreations-official
- Categories
- Cloud Service, AI, Other
Jump to
Setup
Install Second Opinion MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/procreations-official/second-opinion
Follow the installation instructions in the repository README, then restart your MCP client.
Consult multiple AI models, including local, cloud, and enterprise services, to get diverse perspectives on a topic.
Second Opinion turns installed AI coding agents into steerable, parallel worker teams for each other. It handles implementation, testing, investigation, review, documentation, and integration work—not just code review.
Background tasks open a separate, lightweight native task-manager window by default. It shows every active Second Opinion task—even tasks another coding agent started—and lets you steer the work, send follow-up messages, choose the model for the next turn, stop or retry a run, and archive finished tasks. The manager is built with Python's native Tk toolkit rather than Electron, a browser, or an always-on server, so it starts quickly and keeps memory use small on macOS, Windows, and Linux.
Claude Code orchestrating two Grok 4.5 review workers in the native task manager. Each worker has an independent role and native Grok Build context, with model and effort controls, live output, follow-up messaging, retry, stop, and archive actions in one place.
For example, Claude Code can orchestrate five fresh Codex workers using GPT-5.6 Luna atxhigh: one implements, one writes tests, two inspect different risks, and one handles integration. Luna can make that pool much cheaper while parallel work improves throughput. The direction is completely reversible: Codex can orchestrate Claude Sonnet 5 workers, Grok 4.5 workers through Grok Build, or any supported model the selected harness can access. Each worker keeps its native CLI's auth, model access, tools, and safety behavior.
Second Opinion is model agnostic. It routes between installed agent surfaces and the user's existing model/provider setup instead of hardcoding one model. The generated skills teach each parent agent to reason about when another chat is useful, which agent's strongest capabilities fit the scenario, and when a same-agent fresh-context pass is the only sensible option.
For Claude Code, Second Opinion uses the documented non-interactiveclaude -pmode. Model aliases or full model names still pass through to Claude Code with--model.
curl -fsSL https://second-opinion.ssh.codes/install.sh | bash
Install every detected agent skill without prompts:
curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --yes
curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --all --yes
curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --agent codex --yes curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --agent claude --yes curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --agent opencode --yes curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --agent grok --yes curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --agent antigravity --yes
ssh dev@server 'curl -fsSL https://second-opinion.ssh.codes/install.sh | bash -s -- --all --yes'
Update an existing install when a newer version is published:
second-opinion updatedownloads the latest CLI fromhttps://second-opinion.ssh.codes, replaces the local binary only when the published version is newer, and refreshes existing Second Opinion-managed skill files. Usesecond-opinion update --all-skillsto refresh every supported skill file orsecond-opinion update --forceto reinstall the published version anyway.
The installer adds thesecond-opinionCLI to~/.local/binand writes only Second Opinion-owned skill files:
Second Opinion does not edit model settings, provider credentials, hooks, MCP servers, permissions, or app config. If one of those skill files already exists and was not generated by Second Opinion, the installer skips it unless you pass--force.
second-opinion status second-opinion ask auto --from codex --cwd "$PWD" --mode consult --background -- "Review this change and call out risks." second-opinion ask claude --from opencode --cwd "$PWD" --mode consult --background -- "Find edge cases in the parser." second-opinion ask claude --from codex --cwd "$PWD" --model fable --mode consult --background -- "Review this design using Claude Code's selected model." second-opinion ask grok --from claude --cwd "$PWD" --background -- "Implement only the README command table." second-opinion jobs second-opinion wait JOB_ID
The installed skills teach each agent to start subagents in the background by default. That lets the parent agent continue its own non-overlapping work while the subagent runs. Later, the parent runssecond-opinion wait JOB_IDto collect the subagent output.
Second Opinion can ask a coding harness to use an image-generation tool it already exposes. The manager model first discovers eligible harnesses, then requests a real raster artifact with a strict output contract:
second-opinion image-tools --available --json second-opinion image auto \ --from claude \ --cwd "$PWD" \ --reference screenshots/current-home.png \ --output design/homepage-concept.png \ --background \ --manager none \ -- "Overhaul this homepage into a deliberate, distinctive product design."
Codex's built-inimagegen/image_gencapability is detected automatically.image-tools --jsonreports provider-native generator choices (provider-defaultwhen the harness does not expose a model list).--referenceis repeatable; Codex and OpenCode receive references through their native image/file flags, while other harnesses receive readable local paths and additional-directory access where supported. An explicit target can also try a provider tool that cannot be detected statically. Declare such an existing tool forautorouting withSECOND_OPINION_IMAGE_TOOLS=claude=CreateImage,opencode=imagegen; optionally advertise selectable generators withSECOND_OPINION_IMAGE_MODELS='claude=canvas-v2|canvas-fast'.
Second Opinion does not generate the pixels itself, install an image tool, request credentials, or handle image API keys. The selected coding harness uses its existing authentication, native tools, model access, and safety policy. The command fails when the requested artifact is missing, empty, unchanged, or not a valid PNG, JPEG, WebP, or GIF, so an orchestrator cannot accidentally hand a text-only “design” to its implementation worker.
This enables the exact design handoff suggested in the feedback: generate a visual direction first, inspect it, then give the artifact and original constraints to a design-strong worker such as Claude Opus:
Use--modelto select the coding model supervising the image task. Use--image-modelonly when the native image tool already exposes a particular generator. Generated files must stay inside--cwd, existing artifacts require--force, and normalask/teamusage remains unchanged.
second-opinion teamstarts one independent native harness process and fresh context per worker. The parent remains the orchestrator and can continue working, steer each task, change its next-turn model/effort, and synthesize the results.
Claude Code orchestrating five lower-cost Codex workers:
second-opinion team codex \ --from claude \ --count 5 \ --strategy balanced \ --model gpt-5.6-luna \ --reasoning xhigh \ --cwd "$PWD" \ -- "Implement the feature, add tests, inspect risks, and prepare integration in parallel."
Codex orchestrating Claude or Grok workers works the same way:
second-opinion team claude --from codex --count 5 --strategy build --model claude-sonnet-5 --reasoning xhigh -- "Build these non-overlapping slices." second-opinion team grok --from codex --count 5 --strategy review --model grok-4.5 --reasoning high --manager terminal -- "Review from five distinct angles."
- build: core implementation, tests, edge-case hardening, performance/tooling, and integration/docs.
- review: correctness, security, tests, performance, and product/integration review; workers default to consult mode.
- balanced: a mix of implementation, tests, independent review, security/performance review, and integration/docs.
Repeat--role "..."to provide custom worker assignments. Use--mode workor--mode consultto force every worker into the same mode. The CLI accepts 1–32 workers, records the team/role/index on every task, opens only one manager, and returns immediately while all workers run in parallel.second-opinion wait TEAM_IDcollects the whole team;second-opinion jobs --team TEAM_IDlists just that pool.
Model and effort values pass through the specialized harness: Codex usescodex execand its reasoning config, Claude Code usesclaude -p --effort, OpenCode usesopencode run --variant, Grok Build usesgrok -p --reasoning-effort, and Antigravity usesagy --effort. Availability and accepted effort levels remain controlled by each installed provider CLI.
Parallel editing needs deliberate decomposition. Built-in roles include collision-avoidance instructions, but custom non-overlapping file or subsystem assignments are safest. Workers are told to re-read files before edits and never discard concurrent changes.
The manager model can query current publicArtificial Analysisdata before choosing workers. This works without an Artificial Analysis API key, account, sign-in, dependency, or configuration:
second-opinion benchmarks --kind models --sort coding --max-cost 0.50 --limit 12 second-opinion benchmarks --kind models --sort agentic --min-intelligence 45 --json second-opinion benchmarks --kind agents --sort agent-score --max-cost 3 --json second-opinion benchmarks --kind all --limit 10 --json
Model results expose the Artificial Analysis Intelligence, Coding, and Agentic indices; average Intelligence Index cost and time per task; model token prices; and speed when published.--kind agentsexposes the harness-specific Artificial Analysis Coding Agent Index plus average coding-task cost, time, steps, and tokens. This matters because a model's score and a particular model+harness combination are different decisions.
Public results are cached under~/.second-opinion/cache/for six hours to keep startup fast and network use small. Use--refreshto fetch immediately or--offlineafter the first fetch. Human and JSON output both preserve visible Artificial Analysis attribution and source URLs. Benchmark scores are routing evidence, not guarantees; the orchestrator should also consider task fit, installed CLIs, available subscriptions, and the exact model ids each harness accepts.
The native manager opens by default for a background task. Choose a separate terminal manager or no window at all per run:
second-opinion ask codex --background --manager app -- "Review the API changes." second-opinion ask claude --background --manager terminal -- "Polish the responsive UI." second-opinion ask grok --background --manager none -- "Explore two implementation options." second-opinion ask opencode --background --no-window -- "Run a quick model-flexible review."
SetSECOND_OPINION_MANAGER=app|terminal|noneto change the default without modifying any agent application or configuration. If Tk is unavailable on a minimal Linux install, the task still starts and the CLI explains how to usesecond-opinion tuior install the distribution'spython3-tkpackage.
Useworkmode by default. Work mode may edit files and should be assigned carefully so two agents do not edit the same files at the same time. Use explicit--mode consultfor read-only review, planning, or risk analysis.
second-opinion app # detached native app window second-opinion tui # interactive manager in the current terminal
Both surfaces operate only on Second Opinion's records under~/.second-opinion/jobs/and provide the same core controls:
- See active, queued, finished, failed, stopped, and archived tasks.
- Read live output without loading unbounded logs into memory. The native app renders headings, emphasis, lists, task lists, quotes, tables, code, and safe clickable web links as Markdown.
- Send a steering message while a task is running; it queues behind the current turn.
- Change the model and provider-native reasoning effort/variant passed to the task's next invocation. Leave either blank to use the provider default.
- Stop, retry, archive, or restore tasks.
- Start a new task with a chosen harness, workspace, mode, and optional model.
The harness is task-specific and stays task-specific: Codex turns run throughcodex exec, Claude Code throughclaude -p, OpenCode throughopencode run, Grok throughgrok -p, and Antigravity throughagy --print. Follow-up messages invoke that same harness with the prior result context. A model change does not hot-swap a provider process that is already running; it applies to the next turn, or you can stop and retry immediately.
Closing a manager window does not stop an agent task. Normal foreground CLI use loads no GUI modules, starts no manager process, and behaves as before. Second Opinion never embeds into or edits the Codex, Claude Code, Grok, OpenCode, or Antigravity applications.
Goal mode is opt-in. Do not use it by default, and do not treat it as the normal Second Opinion workflow.
Use--goalonly when the user explicitly asks to use Second Opinion with goals, or when the user has clearly requested a long-running delegated goal. For targets with a known native goal command, Second Opinion includes that target's/goal ...command in the subagent prompt:
second-opinion ask claude --from codex --cwd "$PWD" --mode work --background --goal "Finish the frontend accessibility pass and report blockers." -- "Work toward this goal in the assigned UI files only."
When a parent agent starts a goal-backed subagent, the parent still owns the outcome. It should record the job id, checksecond-opinion jobs, collect the result withsecond-opinion wait JOB_ID, verify output and edits, and avoid reporting the overall task as finished while the delegated goal is still running or unresolved.
- For visual UI, frontend polish, responsive layout, copy tone, and product/design judgment, prefer Claude Code with the latest/highest Claude model available to you, often an Opus-class model when available.
- For backend work, APIs, data flow, tests, repo-wide edits, debugging, and most general implementation tasks, prefer Codex unless another target has clearly better context or provider access.
- For quick model-flexible exploration, cheap parallel checks, or trying many configured providers, OpenCode is fast and easy to use; output quality depends heavily on the selected model, so verify smaller or cheaper model results more carefully.
- Use Antigravity for Google/Gemini, Vertex, Firebase, Cloud Run, or Google-style orchestration.
- Use Grok Build for broad exploration or implementation spikes when it is installed and speed matters more than precision.
- Codex
- Claude Code
- OpenCode
- Grok Build
- Google Antigravity
The CLI has a central registry for agent commands, skill paths, and task-routing hints. To add another agent, update the registry inbin/second-opinion, add tests, and runsecond-opinion install --agent <new-agent>to regenerate its skill.
second-opinion install # interactive when attached to a terminal second-opinion install --yes # install detected agent skills second-opinion install --all --yes # install all supported skills second-opinion update # update the CLI and managed skills when newer second-opinion uninstall --agent codex second-opinion status --json second-opinion choose --from claude --task "implement auth flow" second-opinion ask auto --from claude --cwd "$PWD" --mode consult --background -- "Investigate failing tests." second-opinion ask codex --from claude --cwd "$PWD" --model gpt-5.6-luna --reasoning xhigh --background -- "Implement the test fixtures." second-opinion team codex --from claude --count 5 --strategy balanced --model gpt-5.6-luna --reasoning xhigh -- "Build and verify this in parallel." second-opinion team claude --from codex --count 5 --strategy build --model claude-sonnet-5 --reasoning xhigh --manager none -- "Implement non-overlapping slices." second-opinion benchmarks --kind models --sort coding --max-cost 0.50 --json second-opinion benchmarks --kind agents --sort agent-score --json second-opinion image-tools --available --json second-opinion image codex --from claude --cwd "$PWD" --reference current.png --output design/concept.png --background -- "Create a stronger visual direction." second-opinion ask auto --from claude --cwd "$PWD" --mode work --background --goal "Finish the migration tests and report blockers." -- "Work toward this goal in the assigned files only." second-opinion ask auto --from claude --cwd "$PWD" --background --manager terminal -- "Open the terminal task manager." second-opinion ask auto --from claude --cwd "$PWD" --background --manager none -- "Do not open a manager window." second-opinion jobs second-opinion jobs --all second-opinion wait JOB_ID second-opinion app second-opinion tui second-opinion commands second-opinion doctor
- No server is required.
- No browser or Electron runtime is required; the optional native window uses Tk and caps displayed log data.
- No API keys are handled by Second Opinion; its benchmark tool reads attributed public pages and needs no Artificial Analysis key.
- Image creation runs through native tools already available in a selected coding harness; Second Opinion does not install generators or handle image API keys.
- Each target agent runs through its own installed CLI.
- Claude Code runs through its documentedclaude -pnon-interactive mode.
- All agent instructions are regular skill files that users can inspect.
- The subagent prompt includes anti-recursion and scope-isolation rules.
- The manager starts only for a Second Opinion background task (unless opened explicitly) and can be disabled with--manager none.
python3 -m unittest discover -s tests SECOND_OPINION_HOME="$(mktemp -d)" bin/second-opinion install --all --yes SECOND_OPINION_HOME="$(mktemp -d)" bin/second-opinion status --json
To test the installer against a local checkout:
python3 -m http.server 8080 SECOND_OPINION_BASE_URL=http://127.0.0.1:8080 bash install.sh --cli-only
Detect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.
Hosted, Stateless & Multitenant Gemini MCP server enables AI assistants to access multimodal AI capabilities, content generation, and reasoning workflows through Google Gemini.
Queries multiple Ollama models to combine their responses, offering diverse AI perspectives on a single question.
The DataFast MCP server lets MCP-compatible clients such as Codex, Claude Code, and Cursor query your analytics and manage your account through natural language.
Atlas Cloud MCP Server (Image / Video / LLM APIs)
A powerful MCP server for AI image, video, and LLM APIs. Integrate models like Seedance and Nano Banana into your workflow with a simple, unified interface powered by Atlas Cloud.
Competitive intelligence platform with 24 tools — monitor competitor pricing, content, positioning, tech stacks, and how ChatGPT, Claude, and Gemini rank your brand.
Free oncology data (research, clinical trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions, exposed as MCP tools.
Integrates Deepseek models with any MCP-compatible client, such as Claude Desktop.
Access DeepSeek's advanced language models via the DeepSeek API.
MCP Server for full Easypanel control via Claude Code, Cursor and Claude Desktop.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
