Provider hosted
Tools: 15

Leia

Leia

Turn any material into a structured course with AI. Lessons, quizzes, and slides — generated autonomously.

https://leia.to/

Use in your AI tool

Connect straight to this server’s public endpoint.

Remote MCP URL
https://mcp.leia.to/mcp

Use on MCPBundles

We add this server to your workspace, walk through sign-in once, then open Studio with tools ready to run.

Last probed Sep 14, 2026 · mcp.leia.to

15tools discovered

Tools discovered (15)

  • Parse Description

    STEP 1. Parse a natural-language course description into structured course data (title, audience, difficulty, focus areas, learning objectives, tone). Call this first when a user wants to create a course. Returns a draftCourseId (newCourseCreationId) you can thread through the rest of the flow.

  • Start Curriculum

    STEP 2. Start async curriculum generation from parsed course data. Returns a jobId — then call wait_for_job(jobId, type:'curriculum') and loop until COMPLETED (do not end your turn). ALL instruction fields are required. Use customInstructions to bound size, e.g. 'Create 3 modules with 2-3 lessons each'.

  • Check Curriculum

    STEP 3 (one-shot check). Poll a curriculum generation job ONCE. Prefer wait_for_job(jobId, type:'curriculum') to block until it finishes. When COMPLETED, returns the generated curriculum under result.modules[]. IMPORTANT: review/curate the curriculum (module & lesson counts, every lesson has a slug) BEFORE calling create_course.

  • Create Course

    STEP 4. Create a LEIA course from a curated curriculum. Pass the curriculum (modules[].lessons[]) reviewed from check_curriculum. IMPORTANT: every lesson MUST have a `slug`. For the RAG flow, pass the draftCourseId so uploaded documents link to the new course.

  • Generate Lessons

    STEP 5. Batch-generate AI lesson content for a course. Returns a job with credit reservation info (estimatedCredits). This takes minutes — then call wait_for_job(jobId) and keep calling until COMPLETED (do not end your turn). QUIZ-type lessons are skipped automatically.

  • Generate Slides

    OPTIONAL. Batch-generate presentation slides for lessons. Takes minutes — call wait_for_job on each returned jobId and loop until COMPLETED. Note: slides use an AI image worker; if it is unavailable the Partner API returns a 500 (infra issue, not credits/auth).

  • Get Course

    Retrieve full course details by LEIA course ID or dashboard slug (modules & lessons). Use this to resolve a courseId from a slug before other operations.

  • Export Pdf

    OPTIONAL. Export course lessons as PDF (async). Omit lessonIds to export all valid lecture lessons. Returns a jobId — call wait_for_job(jobId) until COMPLETED (the job result carries a download URL).

  • Delete Course

    Delete a course by LEIA course ID. This is destructive and cannot be undone.

  • Upload Rag Document

    Upload a source document (by HTTPS URL) as RAG reference material for a course. The server fetches the file and forwards it. Returns a draftCourseId — reuse the SAME draftCourseId in parse_description, start_curriculum, and create_course so the documents inform generation and link to the final course. Supported: PDF, DOC(X), XLS(X), TXT, Markdown, HTML, CSV, RTF.

  • Check Rag Status

    Poll RAG document processing for a draft. Wait until isProcessing is false and all documents are COMPLETED before generating curriculum or lessons.

  • Wait For Job

    Block until a LEIA job finishes, then return its final status and result. USE THIS after any tool that returns a jobId (start_curriculum, generate_lessons, generate_slides, export_pdf) — it long-polls server-side so you don't have to. When it returns 'still running', call it AGAIN immediately with the same jobId to resume — do NOT end your turn or tell the user you'll check back later. Set type:'curriculum' for curriculum jobs. (Shell-capable hosts may sleep briefly between resumes, but this too

  • Check Job

    Poll the status of any LEIA job (lesson generation, slides, etc.) by ID. Returns status and progress (0-100).

  • Cancel Job

    Cancel a QUEUED, PROCESSING, or RETRYING job by ID.

  • Get Credit Balance

    Check the organization's available credit balance before triggering generation (lessons/slides cost credits). Use this for cost-awareness when a user asks to generate a large course.

Get your MCP into directories

A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.

Directory coverage for brands

Frequently Asked Questions

What is the Leia MCP server?

Turn any material into a structured course with AI. Lessons, quizzes, and slides — generated autonomously.

How do I connect Leia to my AI agent?

Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.

How many tools does Leia provide?

MCPBundles probed 15 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.

What authentication does Leia require?

Leia may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.

Maintain this listing

Operate Leia? Verify ownership to take over this directory entry.

Operate Leia?

This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.

Claim this listing