The Cycles MCP Server provides runtime budget authority for autonomous agents, allowing them to check, reserve, spend, and release budget before and after costly operations.
From the registry: Runtime budget authority for AI agents — reserve, enforce, reconcile spend across providers
Please install the `cycles-mcp-server` MCP server into my current AI client (that's you).
Optional prerequisites:
- Cycles API key — Get an API key from runcycles.io, or set CYCLES_MOCK=true for local development without an API key. (https://runcycles.io)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@runcycles/mcp-server"]
- required environment variables:
- `CYCLES_API_KEY`: Cycles API key. (example: `<your-cycles-api-key>`)
- optional environment variables:
- `CYCLES_BASE_URL`: Cycles API base URL. (example: `http://localhost:7878`)
- `CYCLES_MOCK`: Set to 'true' for mock mode (no API key needed). (example: `true`)
Note: Runtime budget authority for autonomous agents. CYCLES_API_KEY required unless CYCLES_MOCK=true.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CYCLES_API_KEYrequiredAPI key for authenticationCYCLES_BASE_URLrequiredURL for the Cycles serverAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.