"Aufgaben von Claude zu Gemini zuweisen, um Token zu sparen" matching MCP servers:

This MCP server enables remote control and management of Claude Code agents, allowing you to execute missions, configure agent personalities, and integrate with other MCP tools.

Odoo MCP server for Claude Code and Claude.ai — turn any self-hosted Odoo instance (15 → 19) into an AI assistant via the Model Context Protocol. 197+ tools, multi-tenant, Bulgaria localization (НАП, ДДС, ЕИК) included.

Fetches YouTube video transcripts, using free captions when available and falling back to Gemini-based transcription for missing or broken captions.

Gemini-powered MCP server for automated code review, analysis, and documentation.

MCP server for overseer.nvim — gives any MCP-capable coding agent running inside Neovim (Claude Code, Codex, Gemini CLI, opencode) the same visibility and control over tasks the user has: list, run, tail, restart, stop. Agent-started dev servers land in the user's own task list instead of becoming invisible orphaned processes.

Local MCP server for generating image assets with Google Gemini (Nano Banana 2 / Pro). Supports transparent PNG/WebP output, exact resizing/cropping, up to 14 reference images, and Google Search grounding.

Enables AI assistants to generate real images via multiple models (OpenAI, Gemini, Recraft, Seedream, Grok, Arrow) and returns usable file paths instead of base64 data.

MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.

MCP server for the BoondManager API, enabling Claude to search, create, and modify records across 36 domains with 158 tools.

Provides comprehensive wallet, token, and smart contract utilities for the Abstract Testnet and Mainnet, including balance checks, transfers, and ERC-20 deployments. It enables users to manage Abstract Global Wallets and generate EOA accounts through natural language commands.

Thin MCP wrapper around the SQD Portal API for blockchain data queries across multiple networks including EVM, Solana, Bitcoin, Substrate, and Hyperliquid. Provides 25 public tools for discovery, cross-chain queries, and chain-specific operations.

Standalone MCP server for Obsidian vaults - hybrid search (FTS5 + vector + cross-encoder reranking), images and PDFs in agent-readable form, Kanban-aware tasks (Tasks-plugin + Dataview formats), structured memory with topic recall, fine-grained read/write tools for optimal token efficiency, and link graph support. Run locally, self-host, or one-click deploy for remote access. OAuth 2.1.

Enables reading any public Shopify storefront's product catalogue with variants, SKUs, and prices, plus its collections, through two read-only MCP tools without needing an app or merchant token.

The interface protocol for AI agents. 8 kernel primitives + 16 stdlib operations to operate any interface. Forge once, run forever — zero AI at runtime. 81 skills across 41 sites.

Read-only MCP server for Pear Protocol that gives Claude access to markets, pair ratios, positions, orders, trade history, and portfolio.

MCP server enabling AI agents to perform cross-chain token swaps through NEAR's intent-based architecture using the Defuse Protocol, with token discovery, quote retrieval, swap execution, and status tracking.

An enhanced MCP server that enables users to interact with NotebookLM while ensuring strict source fidelity and citation accuracy through client-side prompt structuring. It guides Claude to transform user queries into structured prompts that prevent the addition of external knowledge during document analysis.

MCP server for MyAnimeList that enables searching anime/manga, getting details, rankings, seasons, characters, reviews, and user profiles without authentication, and managing personal anime/manga lists with authentication (token required).

Unified MCP orchestration layer that consolidates multiple MCPs into a single interface with semantic tool discovery, code-mode execution, scheduling, and intelligent caching to reduce token usage by 97% and eliminate choice paralysis.

Enables encoding JSON into compact TOON format and decoding TOON back to JSON, reducing token usage for LLM prompts.