Skip to main content

daisyui-mcp

A typed, local Model Context Protocol server for official DaisyUI 5 documentation and agent skills. It is distributed as a normal Python wheel, works with Python 3.10+, and keeps a bundled offline snapshot for predictable development.

Published package: https://pypi.org/project/daisyui-mcp/

Install with uv

Install the MCP server as a user tool:

uv tool install daisyui-mcp

For optional skill-management dependencies:

uv tool install "daisyui-mcp[skills]"

Install with pip

Install the MCP server into the active Python environment:

python -m pip install daisyui-mcp

For optional skill-management dependencies:

python -m pip install "daisyui-mcp[skills]"

For local development, sync the committed lockfile:

uv sync --locked --extra dev --extra skills

Run

The default command serves MCP over stdio:

daisyui-mcp

To configure an MCP client, use the installed executable as its command:

/absolute/path/to/daisyui-mcp/.venv/bin/daisyui-mcp

The compatibility module mcp_server.py remains available for older checkout-based configurations.

MCP surface

Tools:

  • list_components and get_component(name) preserve the original API.
  • search_daisyui(query) searches component and skill metadata.
  • list_skills() and get_skill(name) expose the bundled official skill.
  • refresh_daisyui() refreshes current component docs with cached fallback.
  • install_daisyui_skills(target) installs the official skill tree.
  • daisyui_status() reports content origin, counts, and refresh time.

Resources:

  • daisyui://components
  • daisyui://skills
  • daisyui://install
  • daisyui://status
  • daisyui://component/{name}
  • daisyui://skill/{name}

The MCP server can install skills into the current project with an explicit tool call. The CLI equivalent is:

daisyui-mcp skills install
daisyui-mcp skills install --target ./custom/skills/daisyui

The default target is ./.agents/skills/daisyui. The installer fetches the official DaisyUI skill tree, validates archive paths, and falls back to the packaged SKILL.md if the network is unavailable.

Configure Codex

Install a reusable Codex profile template in the current project:

daisyui-mcp config install

Copy daisyui-mcp.config.toml to $CODEX_HOME/daisyui-mcp.config.toml (usually ~/.codex/), then run:

codex --profile daisyui-mcp

The profile starts one stdio MCP server; its complete tools and resources are available after startup. As a one-time global alternative, run:

codex mcp add daisyui-mcp -- daisyui-mcp serve

See examples/config.toml for the equivalent TOML.

DaisyUI source and refresh behavior

The runtime specification follows the official DaisyUI installation guide:

https://daisyui.com/docs/install/

Current component content is fetched from:

https://daisyui.com/llms.txt

daisyui-mcp refresh stores a JSON snapshot in the platform user cache. The server serves cached content after a successful prior refresh and bundled content when no cache exists or the network is unavailable. The package also bundles current component docs, including aura, megamenu, otp, and tooltip, plus the official skill entrypoint.

Development

uv sync --locked --extra dev --extra skills
uv run --extra dev ruff check .
uv run --extra dev ruff format --check .
uv run --extra dev mypy src tests
uv run --extra dev pytest
uv run --extra dev python -m build
uv run --extra dev twine check dist/*

The project uses a src layout, setuptools with setuptools-scm, strict MyPy, Ruff, pytest, and a committed uv.lock. Git tags such as v0.2.0 determine the package version used by the release workflow.

License

MIT. See LICENSE.

Release files for daisyui-mcp 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for daisyui-mcp 0.2.0
File Size Uploaded
daisyui_mcp-0.2.0.tar.gz 2.2 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for daisyui-mcp 0.2.0
File Interpreter ABI Platform
daisyui_mcp-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 2.3 MB

Release files / daisyui_mcp-0.2.0.tar.gz

Download URL daisyui_mcp-0.2.0.tar.gz
Size 2.2 MB
Tags Source
SHA-256 checksum
How to use checksums
25cf0f9a70fb8e4e0f15cb9ea6bae598875e18ac4eff59e7fa3ce98fa4798c5b
BLAKE2b-256 checksum
How to use checksums
8da2fe3e45ed7870a2a2486af4229c4c5f359360cbb112896705fe950daf3c96
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 22, 2026.

Transparency log

Release files / daisyui_mcp-0.2.0-py3-none-any.whl

Download URL daisyui_mcp-0.2.0-py3-none-any.whl
Size 61.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
eacc5a5aa00973e9a5d81b53643c9ced600669f430d021ed52d24554d69888f1
BLAKE2b-256 checksum
How to use checksums
7b2d2421d7efbeff80d67ca7f8ffd6d8cbbfa2f7b461bc517004eb8d3a73b6e8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 22, 2026.

Transparency log

Release history Release notifications | RSS feed

0.2.1

2 release files

This release

0.2.0 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page