"Rime" matching MCP servers:

A Prime Agent skill that connects to Stripe's official remote MCP server to inspect and manage Stripe resources via OAuth.

Provides a time_now tool to retrieve the current time, enabling time-sensitive queries in AI agents.

Enables agents to coordinate through a shared local project board by reading specs and recent updates, posting progress, blockers, and review handoffs via MCP, while users follow along in a browser.

An agentic AI system that answers time-related questions by calling a time API tool and general questions using an LLM, accessible through a simple chat interface.

The server enables Claude Code to rent, drive, and terminate Prime Intellect GPU pods with hard spend caps, allowing AI agents to provision and manage cloud GPU resources autonomously.

Gives time-blind LLMs and agent frameworks a real clock: current time and timezone, elapsed task duration, countdowns to deadlines, timezone conversion, session heartbeats, cron-style due checks, and session-level timers. This lets locally hosted or self-built models stop hallucinating the time and actually perceive how long a task or conversation has been running.

Enables agents to dynamically schedule thinking-token budgets, reflection passes, and temperature annealing while performing MCTS/process-reward verification, proof checking, and consensus voting through a standard-library STDIO MCP interface.

Enables agents to dynamically allocate test-time compute, including entropy-driven thinking token budgets, temperature annealing, and reflection passes, while verifying reasoning via MCTS search with process reward modeling, counterfactual backtracking, formal proof checking, and majority-vote consensus. Runs as a zero-dependency Python MCP server over STDIO JSON-RPC for integration with Claude Desktop, Cursor, or custom agent runtimes.

Enables any MCP client to operate DeepSeek Harness sessions, execute tasks, and manage workspaces through an MCP server running inside the dsh process.