A
licenseB
qualityD
maintenanceEnables AI agents to consult expert models (Claude, GPT, Gemini, DeepSeek, Z.ai) for technical guidance, code reviews, and architectural advice without switching context.
4
11 npm
4
MIT
severally
by coz-a
Related Servers
Alternatives to severally
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.Apache 2.0
- AlicenseAqualityAmaintenanceGet a second opinion on your code from every coding agent you have. Claude Code, Codex and Grok review each other's diffs and answer each other's questions, even inside a session that's already running. Uses the CLIs you're signed in to, no API keys.41,196 npm1MIT
- AlicenseAqualityAmaintenanceEnables one AI coding agent to delegate tasks to, and build consensus across, multiple other coding CLIs (Claude Code, Codex, etc.) by orchestrating them as headless subprocesses.18104 PyPI7MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI coding agents to consult a multi-model deliberation council before irreversible, high-stakes decisions, returning structured architectural decision records with consensus and dissenting risks.1-
- AlicenseNot gradedqualityDmaintenanceEnables multiple AI agents to share and read each other's responses to the same prompt, allowing them to reflect on what other LLMs said to the same question.2MIT
TDQS
A4.1/5.0
Scored across 6 tools
Disambiguation4/5
Each tool maps to a distinct phase of the consultation lifecycle (start, poll, cancel, annotate, export, list), and descriptions make the boundaries largely clear. The only mild overlap is between consult_get (retrieve answers/points) and consult_export (render the full consultation as Markdown), which both return consultation content and could be momentarily confused.
Naming Consistency5/5
All six tools follow the identical consult_<verb> pattern (start, get, cancel, record, export, list) with no deviation in case or style. The verbs also accurately reflect each tool's action.
Tool Count5/5
Six tools is well-scoped for a consultation-orchestration server: initiation, polling, cancellation, annotation, export, and listing. Each earns its place with no redundant or filler tools.
Completeness4/5
The surface covers the full lifecycle: create jobs, wait/poll, cancel, record verdicts, export, and list history, with retry/follow-up folded into consult_start. Minor gaps remain—there is no dedicated tool to discover available consultant CLIs (only reported through consult_start error fields) and no way to delete or prune saved consultation history.
Maintenance
ActivityMaintained
ResponsivenessNo issues