What runtime or dependencies are required?
No local runtime is needed. The server is accessed remotely via HTTP; only an MCP‑compatible client is required.
@gigili
基本信息
Documentation repository for the https://d3v.tools MCP server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"d3vtools": {
"url": "https://d3v.tools/mcp/tools",
"transport": "streamable-http"
}
}
}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。
点击上方按钮,直接连接服务器端点实时获取工具列表。
D3vtools is a Model Context Protocol (MCP) server that provides AI agents with access to over 100 developer utilities—encoders, decoders, color converters, cryptographic tools, formatters, and more. It is built for AI coding assistants that need to transform data, inspect formats, or convert between units during development.
The server runs at https://d3v.tools/mcp/tools with streamable-http transport and no authentication. Clients like Claude Desktop, OpenCode, or Cursor are configured by adding the URL and transport to their MCP server settings. The server exposes three tools—list_tools_catalog, get_tool_details, and execute_tool—that are meant to be chained: discover available tools, inspect a tool’s API contract, then execute it.
.well-known/mcp.jsonNo local runtime is needed. The server is accessed remotely via HTTP; only an MCP‑compatible client is required.
No authentication is required. The server is open to anonymous requests.
It exposes three tools—`list_tools_catalog`, `get_tool_details`, and `execute_tool`—that collectively provide access to over 100 individual utilities.
Anonymous users are limited to 10 requests per minute, registered free users to 30, and premium users to 1,000+ requests per minute.
All processing happens on the server (Laravel + PHP) or client‑side (in‑browser JavaScript). No external API calls are made.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Agent-Native Terminal

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents
评论