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.
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.