mcp-presentation
MCP server for building presentations (PDF/web) with a task-based async pipeline, enabling session management, project creation, presentation IR saving, git commits, building, and deployment.
README
mcp-presentation
MCP-сервер для сборки презентаций (PDF / web) с task-based async pipeline.
Пакеты (ports & adapters)
| Пакет | Port / роль | Adapter | Артефакт |
|---|---|---|---|
mcp-presentation |
FastMCP + TaskStore | rusqlite | state/tasks.db |
mcp-state |
sessions / workspaces | rusqlite | state/sessions.db |
mcp-git |
GitPort |
gix | bare + worktrees |
mcp-docker |
ContainerRuntime |
bollard | Docker Engine API |
Стек: Python 3.14 · FastMCP · Rust/PyO3 · gix · bollard · rusqlite · Pydantic.
Git v1: init_bare / add_worktree / commit — без CLI, без push (ADR-0011).
Docker: DooD socket через bollard — без docker CLI (ADR-0012).
Deploy v1: локальный copy в out/deployed/ (ADR-0007).
Happy path (MCP tools)
create_session
→ create_project(project_id)
→ checkout_workspace(session_id, project_id) # gix worktree + state
→ save_presentation_ir(session_id, ir_json) # Pydantic validate
→ commit_workspace(session_id, …)
→ build_presentation(session_id, "pdf"|"web"|"web-pdf") # also refreshes out/slides/
→ get_build_status(task_id)
→ get_slide_image(session_id, slide=1) # read PNG only (after build)
→ deploy_presentation(session_id)
Пример IR: examples/demo/presentation.ir.json
JSON Schema: schemas/presentation.ir.schema.json
ADR
→ docs/adr/ · overview docs/architecture/OVERVIEW.md
Dev
uv venv -p 3.14 .venv && source .venv/bin/activate
uv pip install -e ".[dev]"
(cd packages/mcp-state && maturin develop)
(cd packages/mcp-git && maturin develop)
(cd packages/mcp-docker && maturin develop)
maturin develop
pytest -q
Lint / format
make fmt # ruff + rustfmt
make lint # ruff + mypy + rustfmt --check + clippy
make check # lint + pytest
make docker-build # latex-builder + web-builder images
Builder images + worker
→ infra/
build_presentation ставит задачу; BuildWorker делает claim_next, валидирует IR,
компилирует в .tex/.md при необходимости, запускает образ через bollard.
Образы: MCP_LATEX_IMAGE / MCP_WEB_IMAGE.
Диск
state/tasks.db state/sessions.db
projects/<id>.git/
workspaces/<ws_id>/
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.