Eodly MCP server
Read-only MCP server that exposes Eodly's sourced end-of-day reports and team roster to MCP clients, letting you ask questions like "who is slipping this week?" and get answers backed by GitHub and Linear data.
README
Eodly MCP server
Read your team's sourced end-of-day reports and roster from any MCP client, using an Eodly API key.
Eodly sends founders and team leads one sourced report every evening: who shipped, who is silent, who is slipping. Your team checks in from Slack, Telegram, Microsoft Teams, or Discord, and Eodly weighs each claim against the real work in GitHub and Linear. This server exposes those reports to MCP clients such as Claude and Cursor, so you can ask an agent "who is slipping this week?" and have it pull the sourced answer.
Read-only. It cannot change anything in your workspace.
Install
Hosted (recommended)
A remote Streamable HTTP endpoint, nothing to install:
https://eodly.io/api/mcp
Local (stdio)
npx @eodly/mcp
Configure
Create an API key in the Eodly app under Settings → Developer → API keys, then add the server to your client.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"eodly": {
"command": "npx",
"args": ["-y", "@eodly/mcp"],
"env": { "EODLY_API_KEY": "eodly_sk_..." }
}
}
}
Cursor and other MCP clients use the same shape.
Tools
| Tool | What it does | Scope |
|---|---|---|
whoami |
Identify the key: which organization it belongs to and what scopes it holds | none |
list_reports |
Recent end-of-day report summaries, most recent first (limit, 1-50, default 14) |
reports:read |
get_report |
Full structured content of one report by id | reports:read |
list_team |
The team roster: names, roles, departments | team:read |
Environment
| Variable | Required | Default |
|---|---|---|
EODLY_API_KEY |
yes | none. An Eodly API key (eodly_sk_...) |
EODLY_API_BASE |
no | https://eodly.io/api/v1 |
Keys are organization-scoped and read-only. Revoke one at any time in the app.
Links
License
MIT. See LICENSE.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。