ebb-ai — carbon-aware MCP scheduler
@Vitalini
Open-source MCP server that defers non-urgent LLM tasks to the cleanest electricity-grid hour inside a deadline. When the user says "do this later", "by tomorrow", "overnight", "by EOD", "no rush" — the agent auto-routes the task through schedule_task and the MCP picks the cleane
Overview
What is ebb-ai?
A workload scheduler for the agentic-AI economy that defers non-urgent LLM tasks to cheap, low-load grid windows. It integrates with MCP (Model Context Protocol) to offer automatic carbon‑ and cost‑aware scheduling and ships as an npm package and a one‑command Claude Code plugin.
How to use ebb-ai?
Install via npm install -g @ebb-ai/mcp or as a Claude Code plugin (claude plugin install ebb-ai). Add to Claude Desktop’s MCP config. Use MCP tools (get_grid_forecast, schedule_task, check_queue_status) or the @ebb-ai/core library. A Python 3.11+ port is also available.
Key features of ebb-ai
- Automatic deferral of tasks to off-peak grid windows.
- Real-time carbon‑intensity forecasts for seven grid regions.
- 50% cost savings through Anthropic and OpenAI Batch APIs.
- Auditable carbon and cost receipts for every dispatch.
- SQLite‑backed durable queue with retry‑with‑backoff.
- Nine MCP tools for agent hosts (Claude Desktop, Cursor, etc.).
- One‑command Claude Code plugin with slash commands.
Use cases of ebb-ai
- Defer overnight summaries, batch analysis, and compliance scans to cleaner grid windows.
- Reduce inference costs by routing deadline‑tolerant work through Batch APIs.
- Smooth data‑center load curves and support ESG reporting with carbon receipts.
- Schedule document processing with deadline‑aware, grid‑optimal timing.
FAQ from ebb-ai
What dependencies or runtime are required?
Node.js for the npm packages (@ebb-ai/core, @ebb-ai/mcp); Python 3.11+ for the Python port. Anthropic and OpenAI SDKs are optional peer dependencies.
Where does data live?
Grid forecasts are fetched from public APIs (UK National Grid ESO, US EIA, ENTSO‑E, Electricity Maps). The task queue persists locally to ~/.ebb-ai/queue.db.
What transports and auth does it use?
The MCP server communicates over stdio. No authentication is required for the MCP server itself; optional API keys are needed for some grid data sources. Provider SDKs handle Batch API auth.
What are known limits?
Version v0.7, 88+ tests pass. Some grid regions require API keys and fall back to mock data without one. WattTime marginal‑emissions support is on the roadmap.
How does it compare to alternatives?
The README does not discuss alternatives. ebb-ai is focused on carbon‑aware scheduling with native MCP integration for agentic AI workloads.
