dashy-mcp

dashy-mcp

MCP server exposing Dashy's REST API as tools, enabling an LLM to read and edit dashboard config, including sections, items, and top-level config keys.

Category
访问服务器

README

dashy-mcp

MCP server exposing Dashy's REST API as tools, so an LLM can read and edit your dashboard config: sections, items (tiles), and top-level config keys.

Built with FastMCP.

Enabling the API on your Dashy server

Dashy's API is opt-in and disabled by default. Enabling and securing it (via ENABLE_API, API_TOKEN, and/or Dashy's existing user auth) is server-side configuration specific to how you run Dashy, and out of scope for this project - see Dashy's own docs: Enabling the API.

Install

Download a wheel from the latest release and install it as a uv tool (no repo checkout needed):

uv tool install dashy_mcp-*.whl

This puts a dashy-mcp command on your PATH. Register it with Claude Code:

claude mcp add dashy \
  --env DASHY_URL=https://your-dashy-host \
  --env DASHY_TOKEN=<token> \
  -- dashy-mcp

From source

uv sync
cp .env.example .env   # fill in DASHY_URL and DASHY_TOKEN
claude mcp add dashy \
  --env DASHY_URL=https://your-dashy-host \
  --env DASHY_TOKEN=<token> \
  -- uv run --directory /path/to/dashy-mcp dashy-mcp

Config

Env var Required Default
DASHY_URL yes -
DASHY_TOKEN no none (no auth header sent)
DASHY_CONFIG_FILE no conf.yml

Tools

One tool per Dashy API endpoint:

Tool Endpoint
dashy_list_config_files GET /api/config
dashy_get_config GET /api/config/:file
dashy_replace_config PUT /api/config/:file
dashy_get_key GET /api/config/:file/:key
dashy_set_key PUT /api/config/:file/:key
dashy_add_section POST /api/config/:file/sections
dashy_get_section GET /api/config/:file/sections/:sid
dashy_update_section PATCH /api/config/:file/sections/:sid
dashy_delete_section DELETE /api/config/:file/sections/:sid
dashy_list_items GET /api/config/:file/sections/:sid/items
dashy_add_item POST /api/config/:file/sections/:sid/items
dashy_get_item GET /api/config/:file/sections/:sid/items/:iid
dashy_update_item PATCH /api/config/:file/sections/:sid/items/:iid
dashy_delete_item DELETE /api/config/:file/sections/:sid/items/:iid

sid/iid accept either a zero-based index or an exact section name / item title. filename defaults to conf.yml (or DASHY_CONFIG_FILE) on every tool. PATCH-based updates are a shallow merge: only given fields change, and a nested array included in the patch replaces the existing one wholesale.

Development

make help  # list all commands
Command Does
make sync uv sync
make test Offline tests - one per endpoint, mocked HTTP
make test-integration Tests against the live instance (needs DASHY_URL/DASHY_TOKEN)
make build Build wheel + sdist into dist/
make bump-patch / bump-minor / bump-major Bump the version in pyproject.toml + uv.lock
make clean Remove build artifacts

The release workflow (.github/workflows/release.yml) builds and publishes to Releases whenever a v* tag is pushed - so the usual flow is make bump-patch, commit, then tag and push.

The integration suite reads real config and, for the write lifecycle test, creates and then deletes a scratch section named mcp-test-<uuid> - never touches your real sections. Dashy also auto-backs up every write to user-data/config-backups/ as a second safety net.

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