# Omarkeshk Council Ai MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.omarkeshk%2Fcouncil-ai
Registry id: `mcp-registry/io.github.omarkeshk/council-ai`
Status: live (checked 2026-10-27T01:44:11.983Z)

## Verdict

Omarkeshk Council Ai MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 1138 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (100/100) across 10 tools, costing an agent about 3,319 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 1138 ms | 16% of MCP servers |
| p95 handshake latency | 3031 ms | — |
| Checks in 30 days | 4,959 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 3 min | — |
| Agent-readiness score | 100/100 (A) | 94% of MCP servers |
| Tools | 10 | — |
| Tool-list size for an agent | ~3,319 tokens | 44% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "omarkeshk-council-ai-mcp-server": {
      "type": "http",
      "url": "https://mcp.council-ai.app/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http omarkeshk-council-ai-mcp-server https://mcp.council-ai.app/mcp
```

## Tools (10)

- `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 
- `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 i
- `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 p
- `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), th
- `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 re
- `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
- `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-
- `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 re
- `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
- `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,

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.