Council AI is an MCP server with 10 tools an agent can call, among them council_models, council_query, council_query_with_rag. It answers at https://mcp.council-ai.app/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.
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
council_models | List the AI models available to the current user. Returns ID, provider, tier, context window, and capability flags (web search, vision, streaming). Use the IDs returned here as the `models` array argument to council_query / council_query_wi |
council_query | Send a prompt to a council of frontier AI models across 9 labs (Anthropic, OpenAI, Google, xAI, DeepSeek, Qwen, Mistral, Moonshot, z.ai). Returns each model's independent response plus a moderator-synthesized consensus answer with an agreem Inputs: prompt, models, synthesize, synthesisDirective, mode, async |
council_query_with_rag | Like council_query, but first retrieves the most relevant passages from the user's personal Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases) and injects them into every model's prompt. Use when the quest Inputs: prompt, library_query, retrieval_limit, project_id, models, synthesize |
council_result | Fetch the result of a council_query started with async=true. Returns status "running" while the council is still working (wait 30-60 seconds and call again), the full synthesis + per-model responses once complete, or status "failed" with th Inputs: queryId |
council_review | Multi-model code review. Sends a unified diff (or code snippet) to multiple frontier AI models from different labs in parallel, each acting as an independent reviewer with an explicit verdict + findings contract. Returns a verdict-first syn Inputs: diff, focus, context, models, async |
council_usage | Return the user's current monthly cost-budget consumption (current spend, budget cap, percentage used, days until reset). Use to decide whether to warn the user before invoking another council_query, or to suggest using cheaper models. Per |
library_delete | Permanently delete a document from the user's Council RAG library — the record, every indexed chunk, AND the stored file are removed. This cannot be undone; re-adding the document requires uploading it again. Get document IDs from library_l Inputs: documentId |
library_list | List the documents in the user's Council RAG library. Returns id, filename, source type, ingestion status, chunk count, and upload date for each document. No retrieval, no budget consumption. |
library_search | Semantic search over the user's Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases). Returns top-K chunks with source filename and page number. No model call, no budget consumption. Use to find direct quote Inputs: query, limit, project_id |
library_upload | Upload a document into the user's Council RAG library so future council_query_with_rag and library_search calls can retrieve it. Accepts PDF, Word (docx), text, and markdown files as base64 — images are not supported. Max 10MB per file via Inputs: filename, contentBase64, mimeType, projectId, tags |
Every block below points at https://mcp.council-ai.app/mcp. Pick your client and copy.
claude mcp add --transport http council-ai https://mcp.council-ai.app/mcp
{
"mcpServers": {
"council-ai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.council-ai.app/mcp"]
}
}
}{
"mcpServers": {
"council-ai": {
"url": "https://mcp.council-ai.app/mcp"
}
}
}{
"servers": {
"council-ai": {
"type": "http",
"url": "https://mcp.council-ai.app/mcp"
}
}
}{
"context_servers": {
"council-ai": {
"url": "https://mcp.council-ai.app/mcp"
}
}
}{
"mcpServers": {
"council-ai": {
"serverUrl": "https://mcp.council-ai.app/mcp"
}
}
}{
"mcpServers": {
"council-ai": {
"url": "https://mcp.council-ai.app/mcp"
}
}
}name: Council AI
version: 0.0.1
schema: v1
mcpServers:
- name: Council AI
type: streamable-http
url: https://mcp.council-ai.app/mcp{
"mcpServers": {
"council-ai": {
"httpUrl": "https://mcp.council-ai.app/mcp"
}
}
}{
"mcpServers": {
"council-ai": {
"type": "http",
"url": "https://mcp.council-ai.app/mcp"
}
}
}{
"mcpServers": {
"council-ai": {
"url": "https://mcp.council-ai.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.council-ai.app%2Fmcp&type=streamable_http&id=council-ai&name=Council%20AI
It answered our last check on 22 October 2026 in 652 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
10, as returned by the server's own tools/list on 17 September 2026: council_models, council_query, council_query_with_rag, council_result, council_review, council_usage, library_delete, library_list, and 2 more.
It answered our last check on 22 October 2026 in 652 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.council-ai.app/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.omarkeshk. Endpoint host: mcp.council-ai.app. ARD identifier: urn:air:io.github.omarkeshk:mcp:council-ai.
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.