Vancouver
@jameslong
关于 Vancouver
Simple MCP server library for Elixir.
基本信息
配置
工具
未检测到工具
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。
概览
What is Vancouver?
Vancouver is an Elixir library that integrates the Model Context Protocol (MCP) into Phoenix/Bandit servers. It handles initialization, request validation, and provides helper functions to simplify creating MCP tools and prompts. It is for developers building MCP endpoints in their Phoenix applications.
How to use Vancouver?
Add {:vancouver, "~> 0.3"} to your mix.exs, implement tool and prompt modules using Vancouver.Tool and Vancouver.Prompt, configure the server name and version in config.ex, then forward the /mcp route in your router with your modules. Optionally, configure MCP clients like Claude Desktop via mcp-remote.
Key features of Vancouver
- Integrates MCP into Phoenix/Bandit servers.
- Handles initialization and request validation.
- Provides helpers for tools and prompts.
- Supports tools and prompts (sync responses only).
- Simple and extensible for custom needs.
- Published on Hex.pm for easy dependency management.
Use cases of Vancouver
- Expose custom MCP tools from your Phoenix application.
- Add MCP prompts for LLM interactions like code review.
- Integrate MCP server with Claude Desktop using
mcp-remote. - Build simple, synchronous MCP servers with Elixir.
FAQ from Vancouver
Does Vancouver support all parts of the Model Context Protocol specification?
Not yet. Vancouver currently supports tools, prompts, and sync responses (no streaming). The library is simple enough to modify for your needs.
Is Vancouver stable / ready for production?
No. This library is in early development and expects breaking changes.
Why is this library called Vancouver?
Vancouver is the natural home of MCP (Mountain, Coffee, Protocol).
其他 分类下的更多 MCP 服务器
Nginx UI
0xJackyYet another WebUI for Nginx
Inbox Zero AI
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
AutoBrowser MCP
autobrowser-aiBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
评论