Brivvy MCP

Brivvy MCP

Connects AI assistants to your Brivvy workspace so they can use your brand voices, templates, and glossary for on-brand content.

Category
访问服务器

README

Brivvy AI

This repo is your public entry point for Brivvy AI integrations. You get MCP server metadata, install steps, client connection profiles, and release notes.

The implementation stays private. Everything here is safe to publish.

What you connect to

  • Server type: Remote MCP (Streamable HTTP).
  • Production URL: https://mcp.brivvy.io.
  • Auth: OAuth 2.1-style flow with PKCE.
  • Discovery: Use these before you call the JSON-RPC endpoint:
    • https://mcp.brivvy.io/.well-known/oauth-protected-resource.
    • https://mcp.brivvy.io/.well-known/oauth-authorization-server.

Tools you can rely on

These tool names are the public contract. Short descriptions match what the hosted server exposes today (see MCP Server for connection guides, security notes, and FAQs).

Area Tool What it does
Voices list_voices Lists published voices in your workspace.
Voices get_voice Returns tone and style rules for the default or a chosen voice.
Templates list_templates Lists content templates saved in your workspace.
Templates list_discover_templates Lists public templates from the Brivvy community catalog.
Templates get_template Returns the full prompt and instructions for a template you select.

Quick start

Cursor

Add Brivvy as a remote MCP server:

{
  "mcpServers": {
    "Brivvy": {
      "url": "https://mcp.brivvy.io"
    }
  }
}

Connect once, then finish OAuth in the browser when the client asks you to.

Claude

Point your MCP connector at:

  • URL: https://mcp.brivvy.io.
  • Transport: Streamable HTTP.
  • Auth: OAuth.

Claude reads .well-known metadata and walks you through consent.

Workspace scope

Your Brivvy account uses one workspace at a time for MCP. The workspace you last picked on the OAuth screen applies to every MCP client until you authorize again and choose a different one. If you run Cursor and Claude side by side, they do not keep separate workspace picks today.

Sessions and reconnection

Your access token stays short-lived. The client should refresh it with your refresh token. Refresh tokens last 90 days (Amazon Cognito). When that window ends, connect again and run through OAuth.

When something breaks

  • 401 on POST /: Normal before OAuth. Your client should follow the WWW-Authenticate hint and complete discovery.
  • Disconnects right after consent: Check the callback URL, try once more, and make sure you finished the OAuth popup.
  • Token errors: Reconnect so you get a fresh bearer token. Do not reuse an old web session token.
  • No tools listed: Your MCP consent or workspace access may be missing or expired.
  • Wrong workspace: Reconnect and pick the workspace you want on the OAuth screen. That choice applies across all MCP clients on your account.

What lives here

  • mcp/server.json, registry metadata.
  • mcp/install/, Cursor and Claude profiles.
  • VERSIONING.md, how we version this public metadata.
  • CHANGELOG.md, release notes.
  • SECURITY.md, how to report issues.

Internal release and directory workflows stay in the private Brivvy MCP repo.

How to reach us

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选