Skip to main content
Glama
Study Prep MCP Server

Study Prep MCP Server

by tyorus

Study Prep MCP Server

MCP tools to browse and prepare study materials from a local document folder — PDF, Markdown, plain text, and Word files.

The server extracts text and structure locally; your MCP client (e.g. Cursor) generates summaries and practice questions from the returned content.

Tools

Tool

What it does

get_corpus_overview

Categories, file counts, sizes, supported extensions

list_documents

List files with optional category or glob filter

read_document

Read or extract text from one file (PDF page range supported)

search_documents

Full-text search with snippet context

extract_key_terms

Keyword extraction via YAKE (one doc or whole category)

get_document_outline

Headings / outline for structured review

get_study_chunks

Split long docs into numbered study chunks

prepare_study_session

Bundle excerpts, key terms, and AI prompts for a topic

get_quiz_source_material

Labeled excerpts + instructions for Q&A generation

Related MCP server: Mind Forge

Quick start

git clone https://github.com/YOUR_ORG/study-md-mcp.git
cd study-md-mcp

python3 -m venv .venv
source .venv/bin/activate
pip install -e .

# Smoke test on stdio (Ctrl+C to stop)
MD_DOCS_PATH=/path/to/your/study-documents python server.py

Or with uv:

git clone https://github.com/YOUR_ORG/study-md-mcp.git
cd study-md-mcp

uv venv && uv pip install -e .
MD_DOCS_PATH=/path/to/your/study-documents uv run server.py

Environment variables

Variable

Default

Purpose

MD_MCP_NAME

study-md

FastMCP server name

MD_DOCS_PATH

.

Root folder for study documents

Set MD_DOCS_PATH to the folder containing your study files. On WSL with Windows files, use the /mnt/c/... path.

Connect to Cursor

Copy examples/cursor-mcp-config.json and adjust paths:

{
  "mcpServers": {
    "study-md": {
      "command": "/path/to/study-md-mcp/.venv/bin/python",
      "args": ["/path/to/study-md-mcp/server.py"],
      "env": {
        "MD_MCP_NAME": "study-md",
        "MD_DOCS_PATH": "/path/to/your/study-documents"
      }
    }
  }
}

Then ask Cursor to use study-md tools, e.g. “Search my study docs for essay requirements” or “Prepare a study session on offer terms.”

Connect to Claude Desktop (Windows + WSL)

If Claude Desktop runs on Windows but documents live in WSL, see examples/claude-desktop-config.json.

Connect to Claude CLI

claude mcp add study-md \
  -e MD_MCP_NAME=study-md \
  -e MD_DOCS_PATH=/path/to/your/study-documents \
  -- /path/to/study-md-mcp/.venv/bin/python /path/to/study-md-mcp/server.py

Supported formats

Extension

Method

.md, .txt

Direct UTF-8 read

.pdf

Text extraction via PyMuPDF

.docx

Paragraph text via python-docx

Scanned/image-only PDFs are not supported (no OCR).

Document layout

Organize files under MD_DOCS_PATH by category subfolder:

study-documents/
├── notes/
├── exams/
├── essays/
└── reference/

Empty category folders appear in get_corpus_overview with count 0.

License

MIT — see LICENSE.

Available Tools

9 tools
extract_key_termsB

Extract keywords from one document or an entire category using YAKE.

Args:
    relative_path: Optional single file path relative to docs root
    category: Optional category folder when relative_path is not set
    top_n: Number of terms to return (default 20)

Inputs: relative_path, category, top_n. Returns: result

get_corpus_overviewA

Return categories, file counts, total size, and supported extensions in the corpus.

Inputs: no named parameters. Returns: result

get_document_outlineA

Return document outline from markdown headings or heading-like lines.

Args:
    relative_path: Path relative to docs root

Inputs: relative_path (required). Returns: result

get_quiz_source_materialB

Return labeled excerpts and instructions for generating practice Q&A.

Args:
    relative_path: Optional single file path relative to docs root
    topic: Optional search topic when relative_path is not set
    num_excerpts: Number of excerpts to include (default 5)

Inputs: relative_path, topic, num_excerpts. Returns: result

get_study_chunksA

Split a document into numbered study-sized chunks.

Args:
    relative_path: Path relative to docs root
    chunk_chars: Target chunk size in characters (default 3000)
    overlap: Overlap between consecutive chunks (default 200)

Inputs: relative_path (required), chunk_chars, overlap. Returns: result

list_documentsA

List study documents with relative path, size, and type.

Args:
    category: Optional subfolder name (e.g. lpdp, uwa, learn)
    pattern: Optional glob matched against relative path (e.g. *.pdf, lpdp/*)

Inputs: category, pattern. Returns: result

prepare_study_sessionB

Bundle excerpts, key terms, and suggested AI prompts for a study topic.

Args:
    topic: Study topic or search query
    categories: Comma-separated category folders to search (empty = all)
    paths: Comma-separated relative file paths to include directly
    max_chars: Maximum total characters in the bundle (default 12000)

Inputs: topic (required), categories, paths, max_chars. Returns: result

read_documentA

Read or extract text from a study document.

Args:
    relative_path: Path relative to docs root, e.g. lpdp/essay.pdf
    max_chars: Maximum characters to return (default 50000)
    page_start: PDF only — 1-based start page (0 = from beginning)
    page_end: PDF only — 1-based end page inclusive (0 = through last page)

Inputs: relative_path (required), max_chars, page_start, page_end. Returns: result

search_documentsA

Search document text with snippet context around each match.

Args:
    query: Case-insensitive search string
    category: Optional subfolder filter
    max_results: Maximum number of matching files (default 10)

Inputs: query (required), category, max_results. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 9 tools

    Disambiguation5/5

    Each tool targets a unique aspect of study preparation, such as document overview, reading, chunking, keyword extraction, quiz generation, and session bundling. There is no overlap in functionality, making it easy for an agent to select the correct tool.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case, e.g., 'extract_key_terms', 'get_document_outline', 'list_documents'. The naming is predictable and clear throughout.

    Tool Count5/5

    With 9 tools, the set is well-scoped for study preparation. Each tool serves a distinct purpose without redundancy, covering corpus management, document processing, and content generation.

    Completeness5/5

    The tool set covers all common study needs: browsing documents, reading with pagination, extracting outlines, chunking, keyword extraction, quiz material generation, and full session preparation. There are no obvious missing operations like adding or deleting documents, but the server appears to be a read-only study aid, so this is appropriate.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    Appeared in Searches