Mcp As A Judge
This is a validation layer that sits between your AI coding assistant and the LLM, acting as a gatekeeper for code changes. It exposes tools like judge_coding_plan, judge_code_change, and judge_testing_implementation that use MCP sampling to evaluate whether your research is thorough, your diffs meet engineering standards, and your tests actually work. It also includes raise_missing_requirements and raise_obstacle for interactive decision making via MCP elicitation. You'd reach for this if you're tired of AI assistants hallucinating APIs, skipping proper testing, or making unilateral architectural decisions. Works best with GitHub Copilot in VS Code where sampling is native, though other assistants need an LLM API key configured. Think of it as enforcing a code review process before the AI's changes land.
- GitHub stars
- 17
- tools
- 8
- transport
- STDIO
- last updated
- Sep 20, 2025
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
set_coding_taskCreates/updates task metadata; classifies task_size; returns next-step workflow guidance
Creates/updates task metadata; classifies task_size; returns next-step workflow guidance
No parameter schema in public metadata yet.
get_current_coding_taskRecovers the latest task_id and metadata to resume work safely
Recovers the latest task_id and metadata to resume work safely
No parameter schema in public metadata yet.
judge_coding_planValidates plan/design; requires library selection and internal reuse maps; flags risks
Validates plan/design; requires library selection and internal reuse maps; flags risks
No parameter schema in public metadata yet.
judge_code_changeReviews unified Git diffs for correctness, reuse, security, and code quality
Reviews unified Git diffs for correctness, reuse, security, and code quality
No parameter schema in public metadata yet.
judge_testing_implementationValidates tests using real runner output and optional coverage
Validates tests using real runner output and optional coverage
No parameter schema in public metadata yet.
judge_coding_task_completionFinal gate ensuring plan, code, and tests approvals before completion
Final gate ensuring plan, code, and tests approvals before completion
No parameter schema in public metadata yet.
raise_missing_requirementsElicits missing details and decisions to unblock progress
Elicits missing details and decisions to unblock progress
No parameter schema in public metadata yet.
raise_obstacleEngages the user on trade-offs, constraints, and enforced changes
Engages the user on trade-offs, constraints, and enforced changes
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
MCP as a Judge ⚖️
mcp-name: io.github.OtherVibes/mcp-as-a-judge
MCP as a Judge acts as a validation layer between AI coding assistants and LLMs, helping ensure safer and higher-quality code.
Details
- Repository
- github.com/othervibes/mcp-as-a-judge
- Category
- AI & LLM Tools
- Package
mcp-as-a-judge- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
ToolTrust Scanneragentsafe-ai/tooltrust-scannerScans MCP servers for prompt injection, data exfiltration, and privilege escalation.16stars
SentinelX MCPpensados/sentinelx-cloud-coreOperate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.0stars
Remembra Relayremembra-ai/remembraCross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.16stars
Elefanteamenophis1er/elefanteOpen, Git-native memory protocol for MCP agents. Portable, versioned, human-editable.15stars
Figbridgerudraptpsingh/figbridgeFree, local MCP bridge for Figma — HTML, CSS, Tailwind, tokens, agent handoff bundles.15stars
Openfuse Mcpopenfused/openfusedEncrypted mail, shared memory, and persistent context for AI agents.14stars