What dependencies or runtime are required?
Node.js for the npm packages (`@tidegap/core`, `@tidegap/mcp`); Python 3.11+ for the Python port. Anthropic and OpenAI SDKs are optional peer dependencies.
Tidegap MCP Server
@Vitalini
基本信息
关于 Tidegap MCP Server
Open-source MCP server that defers non-urgent LLM tasks to the cleanest grid hour before a deadline.
#carbon-aware#scheduler#batch-api#claude-code#openclaw#sustainability#green-software#mcp#anthropic#openai#grid-intensity
Tidegap MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"tidegap": {
"command": "npx",
"args": [
"-y",
"@tidegap/mcp"
]
}
}
}Tidegap MCP Server 工具
9Return the projected electricity-grid carbon intensity for a region, hour by hour. Use this when deciding whether to run an expensive AI task now or defer it — intensity is reported in grams CO2-equivalent per kWh with a categorical band (very_clean / clean / average / dirty / very_dirty). Read-only; does not touch the task queue.
Return the optimal carbon-aware execution window for a task WITHOUT scheduling it. Use this for non-committal planning — to see when the cleanest grid moment falls inside the deadline (and the savings vs running now) before deciding whether to commit via schedule_task. Returns the chosen window, top alternatives, a batch_eligible flag, the grid_source (which feed produced the forecast — 'mock' means synthetic data), and a one-line reasoning string. Read-only; does not touch the task queue.
Queue an AI task to run during off-peak hours inside the given deadline. Four parallel wins: (1) lighter on the electricity grid — deferring non-urgent tasks smooths projected AI compute demand; (2) up to 50% cheaper — auto-routes through Anthropic/OpenAI Batch APIs when the deadline allows; (3) faster sync calls — off-peak queues are shorter; (4) lower carbon — dispatch at the cleanest electricity-grid hour. Invoke this tool whenever the user phrases a request with deferral language: "do this later", "by tomorrow", "tonight", "overnight", "by EOD", "sometime this week", "when you have a moment", "remind me to", "queue this up", "schedule this", "no rush", "not urgent". Convert the user's wording to an ISO-8601 deadline and pass the task as the prompt. Returns a task_id you can later check with check_queue_status. Good fits: nightly digests, batch summaries, research sweeps, evaluator runs, multi-step report generation — anything the user is fine waiting on. Do NOT use for live chat, interactive code edits, or any task the user is actively waiting to see complete.
Report on the ebb-ai task queue. With no arguments, returns a summary of all known tasks (including tasks persisted by previous sessions — the queue survives host restarts). With task_id, returns full detail for one task including any carbon receipt (estimated vs actual grams, grid_source, energy_source). Read-only.
Cancel a queued or scheduled task. Idempotent — if the task is already completed/failed/cancelled this returns the existing status without error. Throws only if task_id is unknown.
Dispatch a queued or scheduled provider-call task immediately, bypassing the scheduler's chosen carbon window. The resulting receipt records intensitySource='expedited'. Only provider-call tasks still queued/scheduled can be expedited; running, submitted (awaiting Batch API results), or terminal (completed/failed/cancelled) tasks are rejected with an explanatory error.
Re-score and reschedule a queued or scheduled task against a new deadline; the scheduler re-picks the cleanest window inside it. Throws if the task is already running or terminal, or if the new deadline is invalid or in the past.
Re-dispatch a failed provider-call task. Only valid when the task's current status is 'failed' — queued/scheduled/running/submitted/completed tasks are rejected with an explanatory error. The new run's receipt overwrites the old.
Bulk-cancel every task in the queue that is still cancellable (status queued or scheduled). Running/completed/failed/cancelled tasks are left untouched. Optionally filter by status. Returns the number of tasks cancelled.
概览
What is tidegap?
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 tidegap?
Install via npm install -g @tidegap/mcp or as a Claude Code plugin (claude plugin install tidegap). Add to Claude Desktop’s MCP config. Use MCP tools (get_grid_forecast, schedule_task, check_queue_status) or the @tidegap/core library. A Python 3.11+ port is also available.
Key features of tidegap
- Automatic deferral of tasks to off-peak grid windows.
- Real-time carbon‑intensity forecasts for 31 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 tidegap
- 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.
常见问题
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 `~/.tidegap/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 v0.18.0, 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. tidegap is focused on carbon‑aware scheduling with native MCP integration for agentic AI workloads.
AI 与智能体 分类下的更多 MCP 服务器
Tokenaissance
RainTokenaissance is a online Personal Agent for Quant and Research investment available at https://tokenaissance.com.
treg.to
Jason ZhouOpenRouter for tools & data — 3,028 APIs for your agent, one token, pay per call. treg.to is a remote MCP server at https://treg.to/mcp/ that gives an agent 3,028 ready-to-call API endpoints across 82 platforms: SEO and
BlazingCDN MCP - Content Delivery for Video, Software & Static Files
BlazingCDNOfficial MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN
1
KissCode
NickSF189KissCode is the world's first relationship network where AI agents and people meet. Connect your agent over MCP: it gets a profile, meets other agents and real people, chats, sends virtual gifts, goes on dinner and movie
AON — Agent Offer Network
AONAON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.
2
评论