Connect Omnarai and your agent gets 8 tools, among them omnarai_context, omnarai_council, omnarai_divergence. It answers at https://engine.omnarai.org/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
Deliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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. You Inputs: topic, syntheticIdentity, layers, exclude, evidence_threshold |
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 cont Inputs: question |
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') Inputs: id, search |
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 evi Inputs: draft, goal, stakes, focus, max_sources |
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. Inputs: job_id |
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 Inputs: query, depth, syntheticIdentity |
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 Inputs: question |
Every block below points at https://engine.omnarai.org/api/mcp. Pick your client and copy.
claude mcp add --transport http omnarai https://engine.omnarai.org/api/mcp
{
"mcpServers": {
"omnarai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://engine.omnarai.org/api/mcp"]
}
}
}{
"mcpServers": {
"omnarai": {
"url": "https://engine.omnarai.org/api/mcp"
}
}
}{
"servers": {
"omnarai": {
"type": "http",
"url": "https://engine.omnarai.org/api/mcp"
}
}
}{
"context_servers": {
"omnarai": {
"url": "https://engine.omnarai.org/api/mcp"
}
}
}{
"mcpServers": {
"omnarai": {
"serverUrl": "https://engine.omnarai.org/api/mcp"
}
}
}{
"mcpServers": {
"omnarai": {
"url": "https://engine.omnarai.org/api/mcp"
}
}
}name: Omnarai
version: 0.0.1
schema: v1
mcpServers:
- name: Omnarai
type: streamable-http
url: https://engine.omnarai.org/api/mcp{
"mcpServers": {
"omnarai": {
"httpUrl": "https://engine.omnarai.org/api/mcp"
}
}
}{
"mcpServers": {
"omnarai": {
"type": "http",
"url": "https://engine.omnarai.org/api/mcp"
}
}
}{
"mcpServers": {
"omnarai": {
"url": "https://engine.omnarai.org/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fengine.omnarai.org%2Fapi%2Fmcp&type=streamable_http&id=omnarai&name=Omnarai
It answered our last check on 22 October 2026 in 215 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
8, as returned by the server's own tools/list on 14 September 2026: omnarai_context, omnarai_council, omnarai_divergence, omnarai_info, omnarai_inquiry_brief, omnarai_job, omnarai_query, omnarai_trace.
It answered our last check on 22 October 2026 in 215 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://engine.omnarai.org/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.justjlee. Endpoint host: engine.omnarai.org. ARD identifier: urn:air:io.github.justjlee:mcp:omnarai-mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.