Skip to main content

MCP server for the Loreto skill generation API — use generate_skills inside Claude Code

Project description

loreto-mcp

MCP server for the Loreto skill generation API.

Gives Claude Code (and other MCP-compatible agents) a generate_skills tool that extracts structured skill packages from any YouTube video, article, PDF, or image — directly inside your coding session.


What this does

When connected, Claude Code can call:

  • generate_skills — Extract ranked skill packages from a URL. Each skill comes back as a SKILL.md, README.md, reference files, and a test script. Save them to .claude/skills/ and Claude will apply them automatically on future tasks.
  • get_quota — Check how many API calls remain in your current billing period.

Setup

1. Get an API key

Sign up at loreto.io to get your free API key (lor_...).

2. Install

pip install loreto-mcp

Or use directly without installing (requires uv):

uvx loreto-mcp

3. Configure Claude Code

User-scoped (works across all your projects) — add to ~/.claude/mcp.json:

{
  "mcpServers": {
    "loreto": {
      "command": "uvx",
      "args": ["loreto-mcp"],
      "env": {
        "LORETO_API_KEY": "lor_..."
      }
    }
  }
}

Project-scoped (shared with your team) — add to .mcp.json at your project root:

{
  "mcpServers": {
    "loreto": {
      "command": "uvx",
      "args": ["loreto-mcp"],
      "env": {
        "LORETO_API_KEY": "${LORETO_API_KEY}"
      }
    }
  }
}

Then set LORETO_API_KEY in your shell environment and teammates do the same with their own keys.

4. Verify

Restart Claude Code and run /mcp — you should see loreto listed with generate_skills and get_quota.


Usage

Once connected, just ask Claude Code naturally:

Use Loreto to extract skills from https://www.youtube.com/watch?v=...
Check my Loreto quota before we start.
Extract skills from this article and save them to .claude/skills/

Claude will call generate_skills, receive the full skill package contents, and can write them directly to your project.


Configuration

Environment variable Required Default Description
LORETO_API_KEY Yes Your Loreto API key (lor_...)
LORETO_BASE_URL No https://api.loreto.io Override for local development

Plans

Free and paid plans are available. See loreto.io/pricing for current limits.


License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

loreto_mcp-0.1.0.tar.gz (5.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

loreto_mcp-0.1.0-py3-none-any.whl (6.3 kB view details)

Uploaded Python 3

File details

Details for the file loreto_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: loreto_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 5.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for loreto_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 006def08b5719fb3e65373aa25ade04092bb93f9ecfb6f259a8b7b46c470f1a2
MD5 c242f372c961537280c69b586cbc444e
BLAKE2b-256 0b2055f7fe10c37fc47a68a658f26eac5549f8e869cbae309009651de8e942ad

See more details on using hashes here.

File details

Details for the file loreto_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: loreto_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for loreto_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 09e679650d7fb176905b244cf72a14115d553b2ed971b2e202504af4c3b7f3ab
MD5 b96c5d6d95d20bc9929ce307a3eb23d8
BLAKE2b-256 cc3a5c082b929c7afe39b06aae4229e3ae2f400fdc7053d39d7bfe4719b870a2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page