Rebut
Uses the OpenAI Responses API to perform a single budget-limited, evidence-grounded review of explicitly provided text sources, returning structured findings with file/line citations, model metadata, token usage, and estimated cost.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Rebut
로컬에서 바로 실행하는 독립 코드 검토 MCP. Cloudflare Worker는 선택 사항입니다.
OpenAI 또는 Claude API로 제공한 코드·diff를 검토하는 MCP입니다. 자료는 선택한 공급자로 전송합니다.
Claude 지원은 0.3.0 이상에서 rebut set provider anthropic → rebut set api-key → rebut setup --client claude 순서로 설정합니다. 호스트와 공급자는 별도 선택입니다.
빠른 시작
Node.js 24 이상이 필요합니다. macOS Keychain을 사용하는 예입니다.
npm install -g rebut-mcp
rebut set api-key
rebut setup --client codex
rebut doctor --connect등록 후 Codex를 재시작하세요. Linux/env·Vaultwarden 설정은 설치 안내를 참고하세요.
새 설치는 로컬 stdio를 사용합니다. 여러 기기의 예산·요청 장부를 공유하려면 Worker 모드를 선택하세요. 기존 Worker 설정은 유지됩니다.
review는 유료 호출이며 doctor --connect는 유료 검토 없이 연결만 확인합니다. 결과가 불확실하면 같은 요청 ID를 유지하세요.
Related MCP server: gpt-control
사용 안내
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Free, read-only context retention review for RAG and agent workflows. Supply sanitized text with stable source IDs and a token budget; receive a source-linked context pack, token estimates, and exact excerpt-retention results. No web fetching, account access, model calls or payments. Checks text selection, not factual truth or semantic completeness. No API key required.
Synthetic UX reviews, findings, evidence images, and repair prompts. OAuth required.
Limited-beta App Store and Google Play review analysis, source reviews, alerts and reply drafts.
Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA bounded evidence review engine that ingests documents, extracts evidence for a given claim, detects contradictions, and produces auditable evidence packets without hallucinations or open-web research.-
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to request, track, and verify independent cross-model reviews with structured findings, attachment hashes, and provenance receipts via Chrome Bridge, Codex, or Responses transports.MIT
- AlicenseNot gradedqualityBmaintenanceEnables traceable research workflows by searching uploaded sources, verifying citations, routing uncertain or high-risk requests to human review, and streaming answers with an audit trail.MIT
- AlicenseNot gradedqualityAmaintenanceEnables users to inspect workspace-scoped findings and hosted runs, and to prepare or start/rerun existing hosted reviews after explicit confirmation. It provides concise review summaries without exposing raw diffs, full reports, artifacts, screenshots, credentials, or prompt text.2 npmMIT