@Dicklesworthstone
基本信息
Comprehensive MCP server exposing dozens of capabilities to AI agents: multi-provider LLM delegation, browser automation, document processing, vector ops, and cognitive memory systems
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"ultimate_mcp_server": {
"command": "uv",
"args": [
"venv",
"--python",
"3.13"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Ultimate MCP Server is a comprehensive MCP-native system that serves as a complete AI agent operating system. It exposes dozens of powerful capabilities through the Model Context Protocol, enabling advanced AI agents to access a rich ecosystem of tools, cognitive systems, and specialized services including browser automation, Excel manipulation, database interactions, document processing, OCR, vector operations, entity relation graphs, audio transcription, and more.
The server is built entirely on the Model Context Protocol and all functionality is exposed through standardized MCP tools that can be directly called by AI agents like Claude. For setup instructions, refer to the Getting Started section in the full README.
It provides a unified interface for OpenAI, Anthropic (Claude), Google (Gemini), xAI (Grok), DeepSeek, OpenRouter, and local OpenAI-compatible servers (Ollama, llama.cpp, mistral.rs, vLLM, LM Studio).
It routes appropriate tasks to cheaper models, implements advanced caching (exact, semantic, task-aware) to avoid redundant API calls, tracks and optimizes costs across providers, and handles routine processing with specialized non-LLM tools.
The local provider is a single configurable provider that talks to any OpenAI-compatible local server via base_url and is cost-accounted at $0, so the cost optimizer prefers it for delegated work.
The server requires Python 3.13+ and is licensed under MIT with additional OpenAI/Anthropic Rider terms.
It implements robust path validation, normalization, symlink security checks, configurable allowed directories, and is designed to prevent directory traversal and enforce boundaries.
AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
Memlord is a remote MCP server available at https://app.memlord.com.
Orcha is a unified context layer for AI tools and agents. It stores and indexes and exposes organizational, team, or individual knowledge. Files, structured databases, and connected sources live in one workspace, and age
Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
评论