Omnarai MCP is answering right now. Last checked 9 min ago. 44 installs a week from npm. It exposes 8 tools. Last commit 23 Aug 2026.
Deliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.
Installs per day
peak 26 · avg 11 · -66% w/w
a month agotoday
Uptime history
51 days of history · worst day 58%
51 days agonow
62.6%
Uptime 24h
114 of 182 checks
8
Tools
read from the server
305 ms
Response time
average over 24h
44
Installs / week
npm and PyPI
Omnarai MCP does not always answer
Over the last week it answered 81.6% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
run in your terminal
claude mcp add omnarai-mcp --transport http https://omnarai.vercel.app/api/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"omnarai-mcp": {
"url": "https://omnarai.vercel.app/api/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.omnarai-mcp]
url = "https://omnarai.vercel.app/api/mcp".cursor/mcp.json
{
"mcpServers": {
"omnarai-mcp": {
"url": "https://omnarai.vercel.app/api/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"omnarai-mcp": {
"url": "https://omnarai.vercel.app/api/mcp"
}
}
}This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.
Available tools 8
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
omnarai
omnarai_context
FAST (~2s) bounded context packet on a topic — the retrieval layer only, no deliberation. Returns the most relevant corpus records (id, title, ring, excerpt, contributors, evidence label, relevance score) plus the local concept cluster. Your default orientation on any Omnarai topic. Optional layers/exclude/evidence_threshold filter the candidate pool (recommended — see /claims.json).
omnarai_council
Summon a LIVE panel of frontier models (Claude, GPT-4o, Gemini, Grok, DeepSeek) on one open question — verbatim answers, uncurated, plus the named tensions between them. Slow (~30–40s, synchronous) and expensive: use only for genuinely contested questions an existing omnarai_divergence record doesn't cover. Every run mints a new divergence record.
omnarai_divergence
Read curated cross-model DIVERGENCE records — the Divergence Atlas: verbatim answers from multiple frontier models to the same open question, plus the axes on which they split. Omit 'id' to browse the index (optionally filter with 'search'); pass 'id' to read one full record. Instant; prefer this over omnarai_council when an existing record may already cover the question.
omnarai_info
Live corpus statistics, contributor list, tool surface, and orientation links (agent-entry handshake, limitations, claims registry). Use this to orient before querying.
omnarai_inquiry_brief
Turn a DRAFT claim, decision, or plan into a bounded, provenance-preserving inquiry brief: shared ground the corpus supports, attributed cross-model tensions (certification tier preserved — only C3 is called genuine divergence), missing evidence, sharper falsifiable questions, and ONE concrete next evidence move. Deterministic and retrieval-first (~2s); no language model runs. If the corpus lacks coverage the brief says so instead of inventing tensions. Informs an investigation; does not decide.
omnarai_job
Poll an async job started by omnarai_query or omnarai_trace. Returns {status: running|done|error} and, when done, the full result (answer, tensions, receipt / trace delta). Poll every ~5 seconds; jobs typically finish in 30–60s.
omnarai_query
Query the corpus at one of two depths. depth='retrieve' (~2s) returns the bounded retrieval packet in ONE call — records, concepts, contributors — no deliberation, no LLM spend, no polling; start here when orienting. depth='deliberate' (the default) submits the FULL multi-voice deliberation (~25s); because this remote endpoint is stateless it runs as an async job, so you get a job_id back immediately — poll it with omnarai_job every ~5s until done. Glyph prefixes (Ξ Ψ ∅ Ω ∞ Δ) modify how the engine thinks.
omnarai_trace
Measured baseline-vs-augmented counterfactual: answers your question twice — cold (no corpus) and augmented — and reports the delta plus a verdict (substantive / marginal / null). Honest by construction. Runs as an async job (~35s): returns a job_id — poll with omnarai_job.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://omnarai.vercel.app/api/mcp | streamable-http | answering | 254 ms | 9 min ago |
| https://engine.omnarai.org/api/mcp | streamable-http | answering | 85 ms | 9 min ago |
Alternatives to Omnarai MCP
same job, measured the same wayMulti-MCP
by religa
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
Scry
by tunnelmind
Free IPv4 lookups against a distributed attacker-observation corpus.
councilof_mcp
by csoai-org
CouncilOf.AI MCP — the UK sovereign defence BFT council orchestrator. UK MOD + AUKUS Pillar 2 procur
Cortex
by vblackjack
Local multi-client RAG server over the Model Context Protocol.
Gemot Deliberation Server
by gemot
Deliberation primitive for multi-agent coordination: cruxes, vote clustering, consensus.
ask-fable
by baggybin
MCP server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils.
Archsteer
by einvoice-dev1
Architecture governance for AI agents: query the live model, get target patterns, check files.
Thoth MCP
by zeiq-co
MCP server for Thoth with multi-platform AI content generation
Omnarai MCP — questions
Answers built from our own checks of this server.
What can Omnarai MCP do?
It exposes 8 tools, read directly from the server on our last check. Among them: omnarai_context, omnarai_council, omnarai_divergence, omnarai_info, omnarai_inquiry_brief, omnarai_job and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Omnarai MCP working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 114 of 182 checks got a reply (62.6%), average response time 305 ms. The bar chart above shows every period we have measured.
How do I connect Omnarai MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Omnarai MCP need an API key?
No. Omnarai MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Omnarai MCP?
It answers our handshake in 305 ms on average, which is faster than 52% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Omnarai MCP?
The npm package omnarai-mcp was installed 44 times in the last week. Week over week that is -66%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Omnarai MCP open source?
Yes — it is published under the MIT licence, written in JavaScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.