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
5 npm
4
MIT
severally
by coz-a
Related Servers
Alternatives to severally
No user-submitted related servers found.
Related Servers
- 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.186MIT
- 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.-
- 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
LLM Council MCPofficial
AlicenseNot gradedqualityDmaintenanceEnables Claude Code to consult external LLMs (GPT, Gemini) through multi-turn sessions for second opinions, parallel consultations, and web-grounded research.MIT- AlicenseAqualityBmaintenanceEnables multi-agent council workflows for coding assistants, providing parallel independent reviews, plans, brainstorms, validation, and research with strict read-only boundaries.6MIT
TDQS
A4.4/5.0
Scored across 6 tools
Disambiguation5/5
Each tool targets a distinct lifecycle stage: start, get, cancel, record, export, list. No two tools overlap in purpose; consult_get and consult_list both read state but one is for a specific job/group and the other is a session overview, which is clear from descriptions.
Naming Consistency5/5
All tools follow a consistent consult_verb pattern: consult_start, consult_get, consult_cancel, consult_record, consult_export, consult_list. The verb is always second and snake_case is used throughout.
Tool Count5/5
Six tools cover the full consultation workflow without redundancy: start, poll/get, cancel, record verdicts, export, and list. This is a well-scoped set for a single-purpose server.
Completeness4/5
The lifecycle is complete: create, read, cancel, record, export, list. The only minor gap is no explicit delete/cleanup tool for history, but that is not essential to the core workflow and can be handled outside the server.
Maintenance
ActivityMaintained
ResponsivenessNo issues