What does Cycles MCP Server do?
It provides runtime budget authority for autonomous agents, allowing them to check, reserve, spend, and release budget before costly operations like LLM calls or API invocations.
@runcycles
基本信息
AI agents call LLMs, invoke tools, and hit APIs — but have no built-in way to cap spend. A single agent loop can burn hundreds of dollars before anyone notices. Cycles MCP Server gives any MCP-compatible agent a runtime budget authority: tools to check, reserve, spend, and releas
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"cycles": {
"command": "npx",
"args": [
"-y",
"@runcycles/mcp-server"
],
"env": {
"CYCLES_BASE_URL": "http://localhost:7878",
"CYCLES_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Reserve budget before a costly operation (LLM call, tool invocation, external action). Returns a reservation_id to commit or release later. If decision is not ALLOW, do not proceed with the operation. For lightweight preflight checks without reserving, use cycles_decide instead.
Commit actual usage after an operation completes. Always call this after cycles_reserve whether the operation succeeded or failed. Finalizes the budget charge and releases any unused reserved amount back to the pool.
Release a reservation without committing. Use when an operation is cancelled, skipped, or fails before execution. Returns the released budget amount back to the pool.
Extend the TTL of an active reservation. Use as a heartbeat for long-running operations to prevent the reservation from expiring. Does not change the reserved amount.
Lightweight preflight check — ask whether an action would be allowed without reserving budget. Does not create a reservation. Use at workflow start to decide strategy. For concurrency-safe budget locking, use cycles_reserve instead.
Check current budget balance for a scope. Returns remaining, reserved, spent, allocated, and debt amounts. At least one subject filter (tenant, workspace, app, workflow, agent, or toolset) is required. Do not use as a substitute for cycles_reserve — balances can change between check and action.
List reservations, optionally filtered by status (ACTIVE, COMMITTED, RELEASED, EXPIRED) or subject fields. Useful for debugging stuck reservations or auditing budget usage.
Get details of a specific reservation by ID. Returns status, subject, action, reserved amount, timestamps, and affected scopes. Useful for debugging and monitoring long-running operations.
Record a usage event directly without the reserve/commit lifecycle. Use for fire-and-forget metering of completed operations where pre-estimation is not available. The event is applied atomically to all derived scopes.
Cycles MCP Server gives any MCP-compatible autonomous agent a runtime budget authority — a set of tools to check, reserve, spend, and release budget before and after every costly operation. It integrates with the Cycles platform and is built for platform teams, agent developers, and enterprises that need per-customer or per-workspace spend limits.
Install the package via npm install @runcycles/mcp-server, then add the server to your MCP host’s configuration (Claude Desktop, Claude Code, Cursor, Windsurf, or custom agents). The agent invokes MCP tools like cycles_reserve, cycles_commit, cycles_check_balance, cycles_create_event, and cycles_extend to manage budget at runtime. Built-in prompts help design budget strategy and generate integration code.
It provides runtime budget authority for autonomous agents, allowing them to check, reserve, spend, and release budget before costly operations like LLM calls or API invocations.
No. Because Cycles is exposed as a standard MCP server, any MCP-compatible agent can use it by simply adding the server to its configuration — no SDK integration in the agent’s own code is required.
The server exposes five tools: `cycles_reserve`, `cycles_commit`, `cycles_check_balance`, `cycles_create_event`, and `cycles_extend`.
Platform teams building multi-tenant agent systems, agent developers who want agents to self-regulate (e.g., degrade to cheaper models when budget is low), and enterprises deploying AI agents that need guardrails against runaway spending.
Yes. After a call completes, you can fire `cycles_create_event` with the actual cost. No reservation is needed — the event is applied atomically to all budget scopes for real-time spend tracking.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
评论