"Super User" matching MCP servers:

Spawn parallel autonomous AI agent sessions from a single MCP client. Each agent gets its own workspace, tools, and execution context.

A Model Context Protocol server that provides integration with LeetCode APIs, enabling automated interaction with programming problems, contests, solutions, and user data across both leetcode.com and leetcode.cn platforms.

Enables coding agents to install and manage Paydirt's iOS SDK for user feedback, trial cancellation, and subscription cancellation, with Slack integration and app building.

Exposes the active file and selection(s) from VS Code to MCP clients, enabling CLI coding agents to access current editor context.

A referee for self-improving AI agent loops that mines past sessions, improves workflows, and never stops until told.

Rewrites coding prompts for optimal results with AI IDEs like Cursor by using Claude to add structure, context, and language-specific considerations to user prompts.

Enables Hermes agents to delegate bounded coding tasks to persistent oh-my-pi sessions with isolated git worktrees, live steering, and durable follow-ups, requiring explicit user confirmation before each task.

Enables AI assistants to research topics, generate product requirements and user stories, map codebases, curate context, scaffold full-stack starter projects, and run multi-step development workflows.

Enables Codex to act as a user of a live Claude Code session. It provides tools to send messages, read outputs, manage sessions, and review diffs, allowing mid-task corrections without losing context.

Exposes DeepSeek Harness's coding agent as a model backend via MCP, with user-confirmed task execution and self-inspection/config-patch tools.

Turns product ideas into implementation-ready planning packages including PRD, requirements, user flow, wireframes, data schema, API contracts, and SDK boundaries, with an MCP handoff for coding agents.

Controls coding agents by enforcing structured implementation plans with PRs and commits as work units, requiring user review at each commit checkpoint to prevent agents from going off track. Includes a visualization dashboard for tracking progress in real-time.

Enables autonomous coding agents to escalate complex technical questions to ChatGPT Desktop app via ToS-compliant UI automation, returning expert responses automatically without user intervention.

Enables automated migration of Vue projects to React with intelligent analysis, task management, and learning from user modifications.

Adds a human-in-the-loop checkpoint to MCP-capable AI coding agents, enabling them to pause and request user feedback before executing actions.

A code understanding and generation system designed for Galacean Engine that helps LLMs comprehend the engine architecture and generate high-quality engine code based on user intent.

Enables handing one self-contained job to the Claude Code CLI on the local machine and getting back its final message plus a manifest of the artifacts it produced, without letting Claude write into the user's project. Reads are limited to named directories and all writes stay in a throwaway run directory, so the user reviews the listed files and copies in only what they approve.

Bug-report triage and fix-dispatch MCP for vibe coders. Ask your AI coding agent for a plain-English diagnosis of any user-reported bug — with evidence, blast radius, and a paste-ready fix prompt — then dispatch an automated GitHub fix PR without a second LLM key. 71 tools, Supabase-backed, MIT SDK. npx @mushi-mushi/mcp

Bridges MCP clients such as Claude Code and Cursor to independent Codex app-server sessions, letting them start, poll, steer, review, compact, cancel, and answer prompts for asynchronous Codex tasks over local stdio or a remote authenticated WebSocket. Runs read-only by default, with workspace-write sandboxing only when a user explicitly enables it, and reports job status, model listing, and progress back to the client.

Enables programmatic control of the Z.ai/Zhipu desktop AI coding agent by spawning and owning its headless agent runtime and speaking the ZCode Protocol over stdio, rather than simulating a user. Exposes tools to run and steer chat sessions, inspect conversations and file changes/rewinds, and manage settings, providers, plugins, MCP servers, automations and approvals under a deny-by-default policy with mandatory read-back verification.