AI Workbench MCP

AI Workbench

[License]

AI Workbench supervises AI coding agents, captures evidence, validates work, applies acceptance policy, and produces auditable PR-ready reports.

The PyPI package remains ai-workbench-mcp for this public alpha because the ai-workbench package name is already occupied. The product and CLI are AI Workbench:

pip install ai-workbench-mcpai-workbench --help

Current source metadata targets unpublished ai-workbench-mcp==0.8.0a0. This public alpha consolidates local supervision, evidence capture, validation, acceptance policy, and PR reporting into one product surface.

Public Alpha Warning

The supervisor is the preferred automated evidence path, but daemon, Codex hook, and OpenCode adapter coverage are alpha mechanisms. AI Workbench checks evidence quality and acceptance readiness; it does not prove the work is absolutely correct. High-risk work still requires human review.

Architecture

• AI Workbench supervisor captures local evidence.
• AI Workbench validation writes validation_report.json.
• AI Workbench quality gate writes revision_decision.json.
• AI Workbench PR/report surfaces render accept, needs_review, or block.

Agent output is a proposal. Workbench accepts evidence.

MCP is the connection protocol. AI Workbench MCP is the tool server. Acceptance is decided by the selected validation profile and quality gate. The agent performs. Workbench accepts. MCP connects them.

Quick Start

Register a project once and start the local supervisor:

pip install ai-workbench-mcpai-workbench supervisor setup --project-dir . --task-type code_changeai-workbench supervisor start

Run Codex, OpenCode, Goose, or another supported local workflow in the project. Then inspect the latest report:

ai-workbench supervisor statusai-workbench reports show latest --project-dir .

Render PR-ready artifacts from a finalized run:

ai-workbench pr-gate --run-dir runs/<run_id>

The canonical local run ledger is:

runs/<run_id>/  task_metadata.json  final_prompt.md  model_selection.json  model_output.md  validation_report.json  revision_decision.json  run_log.jsonl  metadata.json  transcript.jsonl  commands.jsonl  workspace/  validation/  artifacts/

validation_report.json and revision_decision.json are the final acceptance authority. Supporting supervisor reports are local evidence, not a substitute for those Workbench artifacts.

Codex Hooks

Install project-local Codex hooks:

ai-workbench setup codex --project-dir . --task-type code_change

Restart Codex or start a new session, open /hooks, review the project hook, and trust it once. Until a hook event is observed, supervisor status reports Codex coverage as configured but unverified.

Goose MCP

AI Workbench still exposes the same MCP tool lifecycle. Register the server with Goose or another MCP host using:

ai-workbench mcp serve

The seven MCP tools remain:

workbench_open_runworkbench_select_policy_packworkbench_select_modelworkbench_record_executionworkbench_validate_runworkbench_quality_gateworkbench_analyze_runs

PR Gate

Workbench PR acceptance consumes real Workbench run evidence:

ai-workbench pr-gate \  --run-dir runs/<run_id> \  --out runs/pr_gate/pr_comment.md \  --json-out runs/pr_gate/pr_decision.json

Outcomes are exactly:

• accept
• needs_review
• block

Missing, unreadable, or scaffold-only evidence blocks. A green CI run, uploaded artifact, sticky PR comment, or model self-claim is not acceptance evidence.

Bootstrap Assets

To add starter configs, prompts, recipes, docs, and the GitHub PR-gate workflow to a repository:

ai-workbench bootstrap --target .

The bootstrap keeps runs/ ignored.

Package Demo

For a package-only synthetic demo:

ai-workbench demo --target ./workbench-first-run

This shows accept, needs_review, and block PR-gate outcomes with fixture evidence. It is not a real target-repository acceptance run.

Development

python -m pip install -e ".[dev,publish]"python -m pytest -q -p no:cacheproviderpython -m ruff check . --no-cachepython -m mypy --no-sqlite-cache --no-incrementalai-workbench demo --target runs/package_demo_smokeai-workbench validate --project ai_workbench_mcp --profile scaffold --run-dir runs/scaffold-smoke

Do not commit runs/. Committed sample evidence must be sanitized and live under examples/.

Docs

• Supervisor docs
• Evidence folder contract
• Transcript schema
• Workspace hygiene
• Confidence rules
• How acceptance works
• Contract baseline
• Package demo walkthrough
• Codex setup
• Codex live-test handoff
• Codex acceptance walkthrough
• Acceptance analytics
• Evidence dashboard
• Event ledger
• Golden-case harness
• Model registry
• Dogfooding guide
• Goose demo walkthrough - recording-ready 3-5 minute public demo runbook
• Policy packs
• PR gate
• Launch issues
• Repository topics
• Create launch issues
• Publishing guide
• Gemini fixture proof
• Codex fixture proof

Recipes:

• Engineering acceptance
• MCP tool smoke
• Docs-only acceptance
• Python package maintenance
• Test-fix acceptance

Sample evidence:

• Accepted tiny Python fix
• Accepted Codex tiny Python fix
• Accepted docs-only smoke
• Needs-review test fix

License

Apache-2.0. See LICENSE. MIT-origin attribution for the consolidated Prove It code is retained in NOTICE.