"ManuS Invitation Code" matching MCP servers:

Wraps the Manus API to expose a generate_image tool, allowing Claude to request image generation through Manus.

Enables planning with Claude Code and high-speed code generation using Cerebras, avoiding API limits while producing quality code with visual diffs.

MCP server integrating Telegram bot with Qwen Code for AI chat, supporting persistent sessions, group chat, and advanced features via mention-based triggers.

Lets agents run a small JavaScript program in a sandboxed worker that composes typed Jev judgments — claim checking, text screening, best-item picking, label classification, passage comparison, and yes/no questions — in a single call, returning only schema-validated results. A companion search tool exposes each judgment's JSON input and output schemas.

Enables MCP clients to check ChatGPT connection status, list live models, and run prompts using a ChatGPT Plus/Pro plan via OpenAI's official OAuth and Responses API.

Claude Code token usage and cost visibility for MCP-capable agents.

A remote MCP server that wraps the Manus API to expose a generate_image tool, enabling Claude to request image generation via Manus.

A multi-persona code review tool that leverages AI agents with distinct expertise (Codex, Toxic Architect, Accessibility Expert) to analyze code quality through the Model Context Protocol.

Enables Claude to generate images by wrapping the Manus API through a remote MCP server with OAuth authentication.

Provides image generation capabilities via Manus AI as MCP tools for Claude AI.

An MCP server for automatic code review using OpenRouter, enabling performance, clean code, SOLID, async, error handling, and security analysis with direct file modification.

A code-execution MCP server for Klaviyo and Shopify analytics, enabling safe JavaScript execution in a V8 sandbox with state persistence across calls.

Enables AI agents to hand high-level objectives to a decision-making core that autonomously reasons, plans, enforces deterministic policy, executes capabilities, evaluates outcomes, and persists semantic memory over stdio or Streamable HTTP.

A local MCP server that lets Claude Code read Ringg AI assistants, knowledge bases, and call history, and make targeted edits to prompts, custom variables, and knowledge base attachments without placing calls.

Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tradeoff analysis without allowing Claude to edit files or run commands.

Enables Claude Code to use GLM (Zhipu) as a cheap, full-capability subagent for file editing, code generation, and bash commands, with automatic routing between Opus and GLM based on task complexity.

Enables retrieving real Claude subscription usage statistics, including the 5-hour session window, weekly limit, and per-model limits, from the same endpoint Claude Code uses.

Enables coding or reasoning agents to request structured judgments from TypeSafe's Jev model at decision points, including choices, scores, claim verification, and code reviews, with probabilities and confidence returned as data.

Lets MCP-compatible AI assistants have read-only conversations with OpenAI Codex CLI for code analysis, review, and Q&A.

Manage voice AI agents from Claude Code, Cursor, VS Code, or any MCP-compatible assistant.