mcp-stepik
MCP server for authoring courses on Stepik. Provides tools for session management, project creation, course synchronization, video upload, and publishing via the Stepik API.
README
mcp-stepik
MCP-сервер для авторства курсов на Stepik: FastMCP (HTTP) + Rust StateStore/TaskStore, workflow как в mcp-presentation.
Пакеты
| Пакет | Import | Роль |
|---|---|---|
mcp-stepik-core |
mcp_stepik |
FastMCP + TaskStore + CLI |
mcp-stepik-state |
mcp_state |
sessions / workspaces (rusqlite) |
Стек: Python 3.12+ · FastMCP · Rust 1.95 / PyO3 · rusqlite · httpx · Pydantic.
Happy path (workflow)
create_session
→ create_project(project_id)
→ checkout_workspace(session_id, project_id)
→ save_course_ir(session_id, ir_json) # Pydantic validate → course.ir.json
→ sync_course(session_id) # task: IR → Stepik API
→ upload_video(session_id, "assets/a.mp4") # task: upload + poll ready
→ get_course_page_url(session_id) # https://stepik.org/course/{id}/
→ publish_course(session_id) # task: is_enabled=true
Пример IR: examples/demo/course.ir.json
Schema: schemas/course.ir.schema.json
Production (Docker / GHCR)
Image: ghcr.io/hewimetall/mcp-stepik
Tags: 0.1.0, 0.1, 0, latest (built on git tag v*).
export STEPIK_CLIENT_ID=...
export STEPIK_CLIENT_SECRET=...
# one-shot
docker run --rm -p 8000:8000 \
-e STEPIK_CLIENT_ID -e STEPIK_CLIENT_SECRET \
-v mcp-stepik-data:/data \
ghcr.io/hewimetall/mcp-stepik:0.1.0
# or compose
docker compose up -d
Container defaults: listen 0.0.0.0:8000, persist under /data (state, projects, workspaces).
MCP endpoint: http://<host>:8000/mcp
OAuth app: https://stepik.org/oauth2/applications/
(Confidential + Client credentials)
If the package is private: echo $GHCR_TOKEN | docker login ghcr.io -u USER --password-stdin
Cursor / HTTP MCP
{
"mcpServers": {
"mcp-stepik": {
"url": "http://127.0.0.1:8000/mcp"
}
}
}
Run locally (HTTP only)
uv sync --extra dev
(cd packages/mcp-stepik-state && maturin develop)
maturin develop
export STEPIK_CLIENT_ID=...
export STEPIK_CLIENT_SECRET=...
export MCP_STEPIK_HOST=127.0.0.1
export MCP_STEPIK_PORT=8000
uv run mcp-stepik
Env for data dirs (optional):
export MCP_STEPIK_STATE=/abs/path/state
export MCP_STEPIK_PROJECTS=/abs/path/projects
export MCP_STEPIK_WORKSPACES=/abs/path/workspaces
Tools
Workflow / state
create_session, get_session, list_sessions,
create_project, checkout_workspace, create_workspace, get_workspace,
list_workspaces, set_active_workspace, remove_workspace,
save_course_ir, sync_course, upload_video, publish_course,
get_task_status, get_course_page_url
Stepik CRUD
Courses / sections / lessons / units / steps:
text, choice, code, video, string, number, matching, sorting, free-answer, review
stepik_health_check,stepik_list_courses, …
Docs
- Changelog:
CHANGELOG.md - Architecture:
docs/architecture/OVERVIEW.md - ADR:
docs/adr/
Dev
make develop
make test
make lint
make cov-rust
Диск
state/tasks.db state/sessions.db
projects/<id>/
workspaces/<ws_id>/course.ir.json
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.