Salyut
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.
Salyut π°οΈ
A council of AI models you can ask for a second opinion β from inside a coding session, a shell, or your household assistant.
Salyut is a small MCP server that fans one question out to several independent free LLMs (different vendors, different training lineages) and returns their answers side by side, each attributed to its model. Different models catch different things, so a quick "ask the panel" is a cheap way to sanity-check a judgment call, break a tie, or get an outside read.
It's named for the Salyut space stations β the place where the crew (here, a panel of models) convenes.
Built with Claude (Opus 4.8). This project β code, tests, and docs β was written collaboratively with Anthropic's Claude.
The panel
Provider | Model | Lineage | In the default roster? |
Cerebras |
| OpenAI-lineage, ~0.2s | β |
Z.ai |
| Chinese (Zhipu) | β |
Groq |
| Meta | β |
| Google (best-effort β thin free quota) | β | |
Mistral |
| European | β οΈ opt-in only |
All run on free API tiers. Mistral is left out of the default roster on purpose: its free tier trains on submitted data, so it's only ever called when a caller explicitly names it (which the household assistant never does). See the wiki for the reasoning.
Related MCP server: AI Council MCP Server
How it's used
In a coding session β registered as an MCP server, so the assistant can call
consult(...)mid-task to get an outside opinion.From a shell β a thin CLI (
consult.cli) for scripting and model bake-offs (e.g. A/B-testing a prompt across models).By a household assistant β as one more MCP tool it reaches for only when genuinely unsure.
Because every caller goes through the one server, a single rate-guard keeps any one of them from draining a thin free-tier bucket the next caller needs.
consult/core.pyβ the providers, the fan-out, and a fail-safe call wrapper (any error becomes an"ERROR: β¦"string, never a crash).consult/ratelimit.pyβ the shared rate-guard (per-provider min-interval + daily cap; fails open for unconfigured providers, closed once a cap is hit).consult/server.pyβ the MCP server (FastMCP, streamable-HTTP at/mcp), exposingconsultandlistmodels.consult/cli.pyβ the shell client (talks to the server by default so the shared guard applies;--directfor offline use).
API keys β six provider keys via environment (
CEREBRAS_API_KEY,ZAI_API_KEY,GROQ_API_KEY,GEMINI_API_KEY,MISTRAL_API_KEY,OPENROUTER_API_KEY). Any you leave unset simply drop out of the roster β no crash. See.env.example.The roster β edit
DEFAULT_ROSTER/FULL_ROSTERinconsult/core.py. Each model is also overridable by env var (e.g.CONSULT_CEREBRAS_MODEL).Rate limits β
GUARD_MIN_INTERVAL/GUARD_DAILY_CAPinconsult/core.py, set from each provider's real free-tier limits.Where it listens β
CONSULT_HOST/CONSULT_PORT(defaults0.0.0.0:8000).Free-model slugs rotate β if a default starts erroring, re-check the provider's model list.
Setup & usage
Install, configure, deploy, and wire it into your tools β see the wiki. (The README describes what Salyut is; the wiki is the step-by-step manual.)
License
GPL-3.0-or-later β see LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
Related MCP Connectors
Ask GPT, Claude, Gemini and Grok at once: one consensus answer plus where they agree and split.
Answers, sources and brand mentions from OpenAI, Perplexity, Gemini, Claude and Grok side by side.
Fan out deep research across multiple AI providers, synthesize into one unified report.
Code review by AI models from different companies, usually two. Shows where they agree and disagree.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceQuery multiple AI models (GPT-4, Claude, Gemini, Grok) in parallel for diverse perspectives. Get different expert viewpoints when stuck or need enhanced reasoning.1MIT
- AlicenseAqualityDmaintenanceMulti-AI Consensus Tool: Query multiple AI models in parallel, synthesize responses for better accuracy, and reduce AI bias through ensemble decision-making.133MIT
- AlicenseNot gradedqualityDmaintenanceLets Claude Code query multiple AI models (Gemini, Grok, ChatGPT, DeepSeek) for diverse perspectives, code reviews, debates, and more.MIT
- AlicenseAqualityDmaintenanceEnables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.129 npm193MIT