A
licenseA
qualityD
maintenanceMCP server orchestrating local CLI agents (Claude Code, OpenAI Codex, Google Gemini) for cross-validation, second opinions, and persona-driven prompting.
18
MIT
cross-review
Related Servers
Alternatives to cross-review
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceMCP servers that let Claude Code delegate to other coding CLIs (Copilot, Codex, Gemini) for cross-model second opinions, structured reviews, and multi-engine consultations.MIT
- AlicenseAqualityBmaintenanceA multi-model AI orchestration MCP server for automated code review and LLM-powered analysis, integrating with Claude Code and OpenCode to orchestrate multiple AI models for code quality checks, security analysis, and multi-agent consensus.637MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables Claude Code to orchestrate multi-model AI consensus by querying GPT-5.2 and Gemini 3 Pro simultaneously, synthesizing high-confidence responses.14 npm1MIT
- FlicenseAqualityBmaintenanceMCP server that enables Claude Code to delegate tasks to DeepSeek and other LLMs, offering 20 tools for code review, analysis, testing, and code generation.201-
- FlicenseNot gradedqualityAmaintenanceEnables multi-agent AI collaboration by connecting Claude Code, OpenAI Codex, and Google Antigravity, providing cross-model code reviews, independent second opinions, and autonomous validation through MCP tools.1-
TDQS
B3.2/5.0
Scored across 28 tools
Disambiguation2/5
Multiple tools serve overlapping purposes: session_start_unanimous vs run_until_unanimous both run rounds until unanimity, ask_peers vs session_start_round both run review rounds, and several session_* readers (session_poll, session_read, session_events, session_metrics, session_peer_reliability_report, session_report) retrieve different but adjacent session state. Descriptions help but boundaries remain blurry, risking misselection.
Naming Consistency3/5
Most names use snake_case, but the pattern is mixed: many tools carry a session_ prefix while others do not (server_info, probe_peers, ask_peers, run_until_unanimous, contest_verdict), and verb-first names are interspersed with noun-based ones (session_metrics, session_report, session_doctor). It is readable but not a predictable, uniform convention.
Tool Count2/5
At 28 tools, the surface is heavy for the domain. Several tools are near-duplicates or aliases (session_start_unanimous/run_until_unanimous, session_preflight_check/session_truthfulness_preflight_check) and could be consolidated, making navigation costly for an agent.
Completeness5/5
The set covers the full cross-review lifecycle: session creation, round execution, polling, reporting, metrics, peer reliability, evidence judging, contesting, recovery, sweeping, finalization, and preflight checks. No obvious operational gap remains for the stated multi-peer review domain.
Maintenance
ActivityActive
ResponsivenessResponsive