"How to use the git clone command" matching MCP servers:

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

Enables two LLMs to play Tic-Tac-Toe against each other autonomously using a shared tool and an SSE relay. The server facilitates agent-to-agent communication by holding tool responses until the opponent makes a move, managing the game state in real-time.

for tokenectomy git workflow

Bridges Kimi Code CLI to OpenAI Computer Use, enabling Kimi to control local macOS applications via MCP.

Wraps OpenAI Codex's computer-use engine to provide MCP tools for Windows screen operations including screenshot, UI automation tree, and input simulation, enabling Claude Code to control the desktop.

Enables Windows desktop automation via MCP, allowing AI agents to control mouse, keyboard, and screen capture with the same interface as Anthropic's computer-use tool.

Enables AI agents to anchor visible on-screen elements to stable DOM targets, preventing click drift during browser computer-use automation.

Enables Claude Code and Claude Desktop to command the jev-ultrafast browser agent in your real Chrome, autonomously pursuing plain-language goals on a given start URL while enforcing a domain-bound safeguard.

A filesystem-based MCP server for AI coding agents to coordinate work across git worktrees by claiming files, checking for conflicts, and logging progress without affecting the repository's git history.

MCP server for l402-kit — enables AI agents (Claude, Cursor, etc.) to autonomously pay Bitcoin Lightning-protected APIs. Tools: l402_fetch, l402_balance, l402_spending_report. Run with: npx l402-kit-mcp

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

Browser use using Typesafe's Jev model

Enables MCP-speaking clients to control a real desktop via the computer_use tool, including clicking, typing, scrolling, dragging, key combos, app focus, and screen/accessibility capture. It also provides a verdict system that verifies whether input actions had their intended effect, with configurable approval modes.

Enables agents using Computer Use to inspect expected browser JavaScript dialogs and respond to OK/Cancel confirmations or text prompts without user intervention. Unexpected dialogs still interrupt the workflow.

A deterministic Mastermind-style cipher lock exposed as MCP tools for benchmarking LLM reasoning and tool-use through a legible duel.

Cross-chain bridge aggregator MCP server for AI agents. Compares routes across LI.FI, deBridge, Relay, Across and Squid to find the best rate. Use when an agent needs to bridge or swap tokens between EVM chains, Solana, or Cosmos. The aggregator of aggregators.

MCP server that lets Claude use your Mac — native apps and the browser — by remembering what it has seen instead of screenshotting every step.

Coordination for parallel coding agents: TTL file claims stored in the git common dir (visible across all worktrees), enforcement hooks that block colliding edits, agent presence, handoff notes, and a git-committed lessons knowledge base with BM25 search. Single static Go binary — no server, no database.

Exactly-once execution for irreversible agent actions: an agent claims the right to run an effect, and a retry after a lost response returns the sealed result instead of charging again. 12 tools over stdio, including a gateway mode where the agent holds a single-use ticket and never the provider key.