mcpField
A
Adonis Docs Mcp

Adonis Docs Mcp

Local
github.com/pimentelleoMemory & Knowledge0Updated 21w ago

About Adonis Docs Mcp

Adonis Docs Mcp gives AI agents searchable access to AdonisJS documentation for versions 5, 6, and 7, plus Edge.js and related resources. It fetches Markdown from official repositories and caches it locally.

Key features

  1. 01Browse AdonisJS documentation versions and sections
  2. 02Fetch and search documentation pages
  3. 03Access Edge.js and Lucid ORM docs
  4. 04Search and inspect the AdonisJS packages registry
  5. 05Cache documentation locally

Use cases

  1. 01Find guidance for an AdonisJS version
  2. 02Retrieve a specific documentation page
  3. 03Look up Edge.js or Lucid ORM references
  4. 04Search for an AdonisJS package

MCP support

Exposes documentation browsing, retrieval, and search tools to MCP clients, covering AdonisJS, Edge.js, Lucid ORM, and the packages registry.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"adonis-docs": {
"command": "uvx",
"args": [
"adonis-docs-mcp"
]
}
}
}
Run commanduvx adonis-docs-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiadonis-docs-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

adonis-docs-mcp

MCP server that gives AI agents fast access to AdonisJS documentation (v5, v6, v7) and Edge.js template engine documentation.

Fetches raw markdown directly from the official GitHub repos and caches locally for speed.

Quick Start

# Run with uvx (no install needed)
uvx adonis-docs-mcp

Integration

Claude Desktop / Claude Code

Add to your MCP settings:

{
  "mcpServers": {
    "adonis-docs": {
      "command": "uvx",
      "args": ["adonis-docs-mcp"]
    }
  }
}
VS Code / GitHub Copilot

Add to .vscode/mcp.json:

{
  "servers": {
    "adonis-docs": {
      "command": "uvx",
      "args": ["adonis-docs-mcp"]
    }
  }
}
Cursor

Add to your MCP config:

{
  "mcpServers": {
    "adonis-docs": {
      "command": "uvx",
      "args": ["adonis-docs-mcp"]
    }
  }
}

Using with Agentfish

Instead of copying these instructions manually, we strongly recommend using Agentfish to automatically install the exact rules, guidelines, and context required for an AdonisJS v7 project directly into your codebase.

uvx agentfish add pimentelleo/adonisjs7-agent

This will automatically create the necessary .cursorrules, CLAUDE.md, or .github/copilot-instructions.md files configured to use this MCP server.

Available Tools

AdonisJS
ToolDescription
list_versionsList all available AdonisJS doc versions (v5, v6, v7)
list_sectionsBrowse the documentation structure for a version
get_docFetch the full markdown content of a specific page
search_docsSearch docs by keyword across titles and content
clear_cacheClear the local documentation cache
Edge.js Templates
ToolDescription
edge_list_sectionsBrowse the Edge.js documentation structure
edge_get_docFetch the full markdown content of an Edge.js doc page
edge_search_docsSearch Edge.js docs by keyword
Lucid ORM
ToolDescription
lucid_list_sectionsBrowse the Lucid ORM documentation structure
lucid_get_docFetch the full markdown content of a Lucid ORM doc page
lucid_search_docsSearch Lucid ORM docs by keyword
Packages Registry
ToolDescription
packages_listList all AdonisJS packages, optionally filtered by category
packages_searchSearch packages by keyword (name, description, category)
packages_getGet full details and README for a specific package

Examples

# List what's available
list_versions()

# Browse v7 docs structure
list_sections(version="v7")

# Read the routing guide
get_doc(permalink="guides/basics/routing", version="v7")

# Search for authentication docs
search_docs(query="authentication", version="v7")

# Search across all versions
search_docs(query="middleware", version="all")

# Browse Edge.js template docs
edge_list_sections()

# Read Edge.js components docs
edge_get_doc(permalink="components/introduction")

# Search Edge.js docs
edge_search_docs(query="slots")

# Browse Lucid ORM docs
lucid_list_sections()

# Read Lucid relationships docs
lucid_get_doc(permalink="relationships")

# Search Lucid ORM docs
lucid_search_docs(query="migrations")

# List all packages
packages_list()

# List authentication packages
packages_list(category="Authentication")

# Search for a package
packages_search(query="jwt")

# Get full details and README for a package
packages_get(name="adonisjs-jwt")

Configuration

Environment VariableDefaultDescription
ADONIS_DOCS_CACHE_TTL3600Cache TTL in seconds (default: 1 hour)
ADONIS_DOCS_CACHE_DIR~/.cache/adonis-docs-mcpCache directory path

Documentation Sources

VersionGitHub RepoStatus
v7adonisjs/v7-docsLatest (default)
v6adonisjs/v6-docsStable
v5adonisjs/v5-docsLegacy
Edge.jsedge-js/edgejs.devTemplate engine
Lucid ORMadonisjs/lucid.adonisjs.comSQL ORM
Packagesadonisjs-community/adonis-packagesCommunity registry

Development

# Clone and install
git clone https://github.com/pimentelleo/adonis-docs-mcp.git
cd adonis-docs-mcp
uv sync

# Run locally
uv run adonis-docs-mcp

# Test with MCP Inspector
npx @modelcontextprotocol/inspector uv run adonis-docs-mcp

Publishing (maintainers)

This project uses PyPI Trusted Publishing via GitHub Actions.

One-time setup
  1. Go to https://pypi.org/manage/account/publishing/
  2. Add a new pending publisher:
    • Project name: adonis-docs-mcp
    • Owner: pimentelleo
    • Repository: adonis-docs-mcp
    • Workflow name: publish.yml
    • Environment name: pypi
  3. Save
Releasing a new version
  1. Update version in pyproject.toml and src/adonis_docs_mcp/__init__.py
  2. Commit and push
  3. Create a GitHub release (tag format: v0.1.0)
  4. The publish workflow will automatically build and upload to PyPI

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.