AI Workbench MCP
This is an acceptance gate layer for AI coding agents, built MCP-first for Goose with Codex local/IDE support coming. It gives you seven tools that open a run, select a validation profile, record agent output, run deterministic checks, apply a quality gate, and render evidence folders with task metadata, validation reports, and accept/needs-review/block decisions. The validation profiles run actual commands like tests and linters, check for required artifacts, and enforce changed-file policies. You'd reach for this when you want auditable proof that an agent run should merge, not just the agent saying "done". It also ships a PR gate workflow that reads the resulting evidence and blocks PRs missing acceptance artifacts.
- tools
- 7
- transport
- STDIO
- last updated
- May 19, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
workbench_open_run
No parameter schema in public metadata yet.
workbench_select_policy_pack
No parameter schema in public metadata yet.
workbench_select_model
No parameter schema in public metadata yet.
workbench_record_execution
No parameter schema in public metadata yet.
workbench_validate_run
No parameter schema in public metadata yet.
workbench_quality_gate
No parameter schema in public metadata yet.
workbench_analyze_runs
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
AI Workbench
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-mcp
ai-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Current source metadata targets unpublished ai-workbench-mcp==0.8.0a0.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
Details
- Repository
- github.com/hrishikesh-thakre/ai-workbench-mcp
- Category
- Monitoring & Observability
- Package
ai-workbench-mcp- Transport
- STDIO
- Registry
- MCP registry, active
Related Monitoring & Observability MCP servers
View all
Exploratory Serverexploratory-io/exploratorySearch and read notes, dashboards, charts, analytics and data published on Exploratory.0stars
Frase SEOfrase-io/mcp-serverSEO, GEO & AI Visibility — research, write, optimize, publish & monitor content. 121 tools.0stars
Pinterest Ads MCP Server by AdKitadkit/pinterest-ads-mcpPinterest Ads MCP server: read campaign analytics and draft campaign changes from AI.0stars
FinCore Agentic Commerceaiproductscout/fincoreAgentic commerce with 58 MCP tools for product search, checkout, A2A negotiation, C-Suite analytics.0stars
Technology Stack Detection APIbr0ski777/tech-enrichment-x402Detect 50+ technologies on any website: CMS, frameworks, analytics, CDN. x402.0stars