ebb-ai runs on your own machine — the client starts it, so there is no endpoint to ping. 74 installs a week from npm. Last commit 31 Oct 2026.
Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 17 October 2026. No other catalogue keeps this.
We read the source, 15 h ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
text = `Could not update the Claude Code settings: ${(err as Error).message}${manual}`;
const child = spawn(cmd, args as string[], { stdio: "ignore", detached: true });
let process = Process()
export const TELEGRAM_API_BASE = "https://api.telegram.org";
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check ebb-ai every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ebb-ai -- npx -y @ebb-ai/mcp
{
"mcpServers": {
"ebb-ai": {
"command": "npx",
"args": [
"-y",
"@ebb-ai/mcp"
]
}
}
}
[mcp_servers.ebb-ai]
command = "npx"
args = ["-y", "@ebb-ai/mcp"]
{
"mcpServers": {
"ebb-ai": {
"command": "npx",
"args": [
"-y",
"@ebb-ai/mcp"
]
}
}
}
{
"servers": {
"ebb-ai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ebb-ai/mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
EBB_DEFAULT_REGION (Default grid region, e.g. GB, US-CAL-CISO, DE), EBB_DB_PATH (SQLite queue path (default ~/.ebb-ai/queue.db)), ANTHROPIC_API_KEY (Dispatch tasks to Anthropic (sync or Batch API)), OPENAI_API_KEY (Dispatch tasks to OpenAI (sync or Batch API)), EBB_EIA_API_KEY (US EIA grid data (CAISO, ERCOT, ISO-NE, PJM), free key), EBB_ENTSOE_SECURITY_TOKEN (ENTSO-E grid data (EU regions), free token), WATTTIME_USERNAME (WattTime account (US marginal emissions)), WATTTIME_PASSWORD (WattTime account password), EBB_ELECTRICITY_MAPS_API_KEY (Electricity Maps fallback feed).
Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed.
Ranks the hours before a deadline for batch jobs and transfers by expected network roughness.
Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.
Test the idea before you build it. Rapidly works inside your AI agent.
Your agent asks before it acts, so the same real-world action is attempted at most once.
Human-as-a-Service for AI agents. Delegate tasks that need a real human, get results via API.
Find the lines your bank will refuse before you send the batch
Route AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions.
Answers built from our own checks of this server.