# Tools > Every listed resource, editors’ picks first. The filters below can be combined. - Search: append `?q=` to the URL. Separate several keywords with spaces; all of them must match. Matches name, repository, tags, professions, description and README. - Filter by type: append `?type=` to the URL. - Filter by profession: append `?profession=` to the URL. Separate several ids with commas; a resource matches when it suits any of them. Ids are listed at https://hebbmind.com/api/v1/professions - Filter by tag: append `?tag=` to the URL. Separate several tags with commas; a resource must carry all of them. Tags are listed at https://hebbmind.com/api/v1/tags Type MCP, Resources for ML / AI or Customer support or Teachers / Students: 88 items. > - ML / AI: Model training, evaluation and LLM application development. > - Customer support: Tickets, customer questions, knowledge-base upkeep and service quality. > - Teachers / Students: Lesson prep, quizzes, grading and course materials; self-study and exam prep. - [MarkItDown-MCP](https://hebbmind.com/ja/mcp/markitdown-mcp.md): [MCP] From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP. - [Knowledge Graph Memory Server](https://hebbmind.com/ja/mcp/memory.md): [MCP] Gives agents long-term memory across sessions with a local knowledge graph of entities, relations and observations, stored in a local JSONL file you can query and edit. Official MCP reference implementation. - [Scrapling](https://hebbmind.com/ja/mcp/scrapling.md): [MCP] MCP server built into the adaptive Python scraping framework Scrapling: supports plain HTTP requests, browser rendering and stealth fetching, and uses CSS selectors to pass only the target content to the AI, saving tokens and filtering out prompt injection. - [PaddleOCR MCP Server](https://hebbmind.com/ja/mcp/paddlepaddle-mcp-server.md): [MCP] Official PaddleOCR MCP: text recognition and layout parsing for images and PDFs (PP-OCR, PP-StructureV3, PaddleOCR-VL), returning text or Markdown. Runs inference locally, or calls the official API or a self-hosted service. - [Sequential Thinking MCP Server](https://hebbmind.com/ja/mcp/sequentialthinking.md): [MCP] Provides a sequential_thinking tool that guides the model to break complex problems into revisable, branching steps. Good for planning, analysis and tasks that need careful iteration. Official MCP reference server. - [Reactive Resume MCP](https://hebbmind.com/ja/mcp/reactive-resume.md): [MCP] Official remote MCP for the open-source resume builder Reactive Resume: agents draft and edit resumes and cover letters, export PDFs and track applications; job-based scoring and tailoring need an AI provider set in the app. Needs a free rxresu.me account or a self-hosted instance. - [@agent-infra/mcp-server-browser](https://hebbmind.com/ja/mcp/browser.md): [MCP] Browser automation MCP server open-sourced by ByteDance in the UI-TARS-desktop repo: drives pages through Puppeteer accessibility data with an optional vision mode, running locally over stdio or remotely over SSE or Streamable HTTP. - [Vibe-Trading](https://hebbmind.com/ja/mcp/vibe-trading.md): [MCP] Trading research agent from HKU's HKUDS whose MCP server offers 70+ tools for quotes, financials, backtesting and research across A-shares, Hong Kong and US stocks and crypto. Needs local Python; HK, US and crypto research need no API key. For research only; not investment advice. - [Cognee MCP](https://hebbmind.com/ja/mcp/cognee-mcp.md): [MCP] Runs the cognee memory engine as an MCP server whose remember, recall and forget tools write documents and conversations into a knowledge graph and vector store for cross-session retrieval. Start it with Docker or uv first; needs an LLM API key by default, or connect to Cognee Cloud. - [Graphiti MCP Server](https://hebbmind.com/ja/mcp/getzep-mcp-server.md): [MCP] Writes conversations and business data into Graphiti's temporal knowledge graph so agents can retrieve long-term memory by entity, fact and time. Open source from Zep; start FalkorDB or Neo4j and the server with Docker first, and configure an LLM API key. - [Arize Phoenix MCP Server](https://hebbmind.com/ja/mcp/phoenix-mcp.md): [MCP] Connects to the Arize Phoenix observability platform so agents can query LLM traces and sessions, manage prompts, browse datasets and read experiment evaluation results. Maintained by Arize; needs a self-hosted or cloud Phoenix instance. - [Presenton](https://hebbmind.com/ja/mcp/presenton.md): [MCP] Open-source AI presentation generator that builds slides from a topic or uploaded documents and exports PPTX or PDF, with a built-in MCP endpoint for agents. Good for lesson decks and reports. Self-host with Docker and configure an LLM API key, then have an admin create an MCP key. - [Local Deep Research](https://hebbmind.com/ja/mcp/local-deep-research.md): [MCP] Deep research assistant that runs locally with a built-in MCP server: searches arXiv, PubMed, Wikipedia and more over multiple rounds and writes cited reports. Needs Python 3.12+, uv and an LLM (local Ollama or an API key); web search needs SearXNG or similar. Runs take minutes to half an hour. - [Gemini Notebook CLI & MCP Server (notebooklm-mcp-cli)](https://hebbmind.com/ja/mcp/notebooklm-mcp-cli.md): [MCP] Unofficial CLI and MCP that let agents work with NotebookLM (now Gemini Notebook): bulk-import sources, ask questions with citations, and generate audio overviews, quizzes, flashcards, mind maps and slides. Uses undocumented APIs and may break; needs a Google sign-in and uv. - [Zotero MCP](https://hebbmind.com/ja/mcp/zotero-mcp.md): [MCP] Connects to your local or cloud Zotero library: search by title, full text or semantics, read PDFs and annotations, add items by DOI and organize collections. Needs Python 3.10+; for local mode, enable the local API in Zotero settings first. - [Excalidraw MCP App Server](https://hebbmind.com/ja/mcp/excalidraw-mcp.md): [MCP] Excalidraw's official MCP App: streams hand-drawn-style architecture diagrams and flowcharts into the conversation, with full-screen editing. Remote endpoint at https://mcp.excalidraw.com; requires a client that supports MCP Apps, such as Claude or ChatGPT. - [arXiv MCP Server](https://hebbmind.com/ja/mcp/arxiv-mcp-server.md): [MCP] Search and download arXiv papers and read the authors' LaTeX source section by section, export BibTeX and follow topic updates, with papers cached locally. No API key needed. - [Paper Search MCP](https://hebbmind.com/ja/mcp/paper-search-mcp.md): [MCP] Unified search across 20+ academic sources including arXiv, PubMed, bioRxiv, Semantic Scholar and OpenAlex, returning deduplicated, normalized results and downloading full text via open-access channels first. Most sources need no API key. - [Tavily MCP Server](https://hebbmind.com/ja/mcp/tavily-mcp.md): [MCP] Four tools for real-time web search, page content extraction, site mapping and full-site crawling, available as a remote server or run locally. Maintained by Tavily; needs an API key or OAuth sign-in, and a free account is available. - [PaperBanana](https://hebbmind.com/ja/mcp/paperbanana.md): [MCP] Turns a paper's method description (text or PDF) or data files into publication-ready diagrams and plots, with several AI reviewer roles refining each figure. Needs an OpenAI or Gemini API key (billed per image), Python and uv. A community reimplementation, not by the original paper's authors. - [MCP Memory Service](https://hebbmind.com/ja/mcp/mcp-memory-service.md): [MCP] Self-hostable long-term memory for agents, offering MCP, a REST API and a web dashboard: semantic search, knowledge graph and automatic memory consolidation. Embeddings are computed locally; choose SQLite, Cloudflare or Milvus as the backend. - [Telegram MCP](https://hebbmind.com/ja/mcp/telegram-mcp.md): [MCP] Uses Telethon to operate Telegram as your personal account: search, send and receive messages, schedule sends, and manage contacts, groups and channels across 80+ tools, with an optional read-only mode. Needs a Telegram API ID and runs locally as a service. - [Slack MCP Server](https://hebbmind.com/ja/mcp/slack-mcp-server.md): [MCP] Community-maintained Slack MCP: reads channel, DM and thread history, searches messages and fetches unread messages; write actions like posting are off by default and must be enabled explicitly. Works with user OAuth or bot tokens over stdio, SSE or HTTP. - [MATLAB MCP Server](https://hebbmind.com/ja/mcp/matlab-mcp-core-server.md): [MCP] MathWorks' official server that lets agents start your local MATLAB, write and run scripts and unit tests, and check code style and potential errors, for computing, simulation and data analysis. Needs a licensed MATLAB R2021a+ and the downloaded server binary. - [MCPVault](https://hebbmind.com/ja/mcp/mcpvault.md): [MCP] Lets agents read and write your local Obsidian vault directly: search notes, append to daily notes, tidy tags and properties, and summarize reading or research notes by topic. No need to open Obsidian or install plugins; access is limited to the vault and can be read-only. Needs Node.js 20+. - [Qdrant MCP Server](https://hebbmind.com/ja/mcp/mcp-server-qdrant.md): [MCP] Uses the Qdrant vector database as a semantic memory layer for agents: store information and retrieve it by meaning, connecting to a remote instance or a local path, with FastEmbed generating embeddings by default. Maintained by Qdrant. - [ROS MCP Server](https://hebbmind.com/ja/mcp/ros-mcp-server.md): [MCP] Connects LLMs to ROS and ROS 2 robots: publish and subscribe to topics, call services and actions, set parameters, and read sensor and robot state, without changing robot code. The robot side needs rosbridge running. - [DocuTranslate](https://hebbmind.com/ja/mcp/docutranslate.md): [MCP] Local LLM-powered document translator for PDF, Word, Excel, EPUB, SRT subtitles and more; Word and Excel keep their formatting, glossaries can be built automatically, and agents can submit jobs via MCP. Needs uv and an OpenAI-compatible API key; translated PDFs lose the original layout. - [Jupyter MCP Server](https://hebbmind.com/ja/mcp/jupyter-mcp-server.md): [MCP] Connects agents to live Jupyter notebooks: read, write, insert and execute cells and read multimodal outputs like charts, for interactive data analysis. Bring your own JupyterLab or JupyterHub; open source, maintained by Datalayer. - [Zotero MCP Plugin](https://hebbmind.com/ja/mcp/cookjohn-zotero-mcp.md): [MCP] A Zotero 7 plugin with a built-in MCP server: agents search your local library (title, author, tags, full text), read PDF full text, abstracts, notes and highlights, and create notes and tags. Needs Zotero desktop with the plugin enabled; semantic search needs OpenAI or Ollama embeddings. - [MCP Servers for Google Cloud Genmedia APIs](https://hebbmind.com/ja/mcp/mcp-genmedia.md): [MCP] Experimental open-source generative media MCP servers from Google Cloud: Nano Banana images, Veo video, Gemini TTS and Chirp voices, Lyria music, and AVTool for compositing. Each registers separately; needs a billing-enabled Google Cloud project and gcloud login; AVTool needs FFmpeg. - [Atlassian MCP Server](https://hebbmind.com/ja/mcp/atlassian-mcp-server.md): [MCP] Atlassian's official hosted remote MCP: access Jira, Confluence, JSM, Bitbucket, Loom and more with OAuth or an API token. Works with Atlassian Cloud sites only. - [Nano Banana Gemini CLI Extension](https://hebbmind.com/ja/mcp/nanobanana.md): [MCP] Google's official Gemini CLI extension with a built-in MCP server: Nano Banana image generation and editing, photo restoration, icons, textures, step-by-step storyboards and diagrams. Needs Node.js and a Gemini API key; for Claude Code or Codex, clone and build the repo first. - [Pixelle MCP](https://hebbmind.com/ja/mcp/pixelle-mcp.md): [MCP] Turns ComfyUI workflows into MCP tools with no code, covering generation and conversion across text, image, speech and video; works with local ComfyUI or RunningHub in the cloud. Start the server with uvx pixelle and configure an LLM first. - [anymd](https://hebbmind.com/ja/mcp/pdf-reader-mcp.md): [MCP] Converts PDF, Word, PowerPoint, Excel, EPUB, web pages and images to clean Markdown locally, keeping page anchors, tables and two-column reading order, with full-text search across folders. Formerly pdf-reader-mcp; no uploads, no API key. Needs Node.js 18+; OCR for scans needs tesseract. - [Neo4j Cypher MCP Server](https://hebbmind.com/ja/mcp/mcp-neo4j-cypher.md): [MCP] Graph database MCP server from Neo4j Labs: reads the graph schema and runs read and write Cypher queries, with read-only mode, query timeouts and response token limits. Needs a Neo4j instance with the APOC plugin enabled. - [Jina AI MCP Server](https://hebbmind.com/ja/mcp/jina-ai-mcp.md): [MCP] Jina AI's official remote MCP: converts web pages and PDFs to Markdown, searches the web, arXiv, SSRN and images, and offers screenshots, reranking and semantic dedup. Reading tools work without a key (rate-limited); search and rerank need a Jina API key. - [LINE Bot MCP Server](https://hebbmind.com/ja/mcp/line-bot-mcp-server.md): [MCP] Official from LINE: connects to a LINE Official Account through the Messaging API to push or broadcast text and Flex messages, manage rich menus, and look up followers and user profiles. Needs a channel access token; currently in preview. - [Google Docs, Sheets, Drive, Gmail & Calendar MCP Server](https://hebbmind.com/ja/mcp/google-docs-mcp.md): [MCP] One server for Google Docs, Sheets, Drive, Gmail and Calendar: draft and format documents, handle comments, organize sheets and charts, triage email and schedule events. Create an OAuth client in Google Cloud and run the auth command once; needs Node.js. - [WPS Skills](https://hebbmind.com/ja/mcp/wps-skills.md): [MCP] Lets agents operate WPS Office Writer, Spreadsheets and Presentation on your computer through 200+ MCP tools covering formulas, pivot tables, charts, comments, slide styling and animation. Requires WPS; clone, build from source and install the WPS add-in. Runs on macOS, Windows and Linux. - [Redis MCP Server](https://hebbmind.com/ja/mcp/mcp-redis.md): [MCP] Redis's official MCP server: read and write strings, hashes, lists, streams, JSON and other data structures in natural language, with vector indexing and search and pub/sub. Bring your own Redis instance; runs via uvx. - [YouTube Transcript Server](https://hebbmind.com/ja/mcp/mcp-server-youtube-transcript.md): [MCP] Fetches captions and transcripts for YouTube videos and Shorts, with language selection and fallback, optional timestamps and sponsor segments filtered by default. No API key for transcripts; the optional visual analysis tool needs a TwelveLabs API key and a direct video URL. - [Chroma MCP Server](https://hebbmind.com/ja/mcp/chroma-mcp.md): [MCP] Chroma's official MCP: lets agents create and manage collections, add documents, and retrieve them with vector search, full-text search and metadata filters. Connects to in-memory or local persistent stores, self-hosted instances or Chroma Cloud. - [Discord MCP](https://hebbmind.com/ja/mcp/discord-mcp.md): [MCP] Lets agents send and read channel messages and DMs through your own Discord bot, and manage channels, roles, member timeouts and scheduled events, useful for running a community or player support on Discord. Create a bot in the Discord Developer Portal for a token; needs Docker. - [mcp-pandoc](https://hebbmind.com/ja/mcp/mcp-pandoc.md): [MCP] Converts between Markdown, Word, HTML, LaTeX, EPUB and more with Pandoc, exports PDF and PPTX, and can apply a Word template for consistent styling, handy for formatting manuscripts and handouts. Needs Pandoc and uv; PDF export also needs TeX Live. - [YouTube MCP Server](https://hebbmind.com/ja/mcp/mcp-youtube.md): [MCP] Uses yt-dlp to pull YouTube subtitles into the agent, so asking it to summarize a video gets you the key points; handy for teachers prepping lessons, researchers and creators. No API key, but needs yt-dlp (Homebrew or WinGet) and Node.js. - [lean-lsp-mcp](https://hebbmind.com/ja/mcp/lean-lsp-mcp.md): [MCP] MCP server for the Lean 4 theorem prover: lets agents read proof goals, diagnostics and definitions and search theorems via LeanSearch and Loogle, helping mathematicians and students with formal proofs. Needs uv and the Lean toolchain; run it from the Lean project root. - [Anki MCP Server](https://hebbmind.com/ja/mcp/anki-mcp-server.md): [MCP] Lets agents work with Anki flashcards: review due cards and grade them, create cards in bulk, manage tags, media and note types, and view study stats. Needs Anki Desktop with the AnkiConnect add-on; still in beta. - [Stata MCP](https://hebbmind.com/ja/mcp/stata-mcp.md): [MCP] Connects Stata to VS Code or Cursor and exposes a local MCP endpoint so Claude Code or Codex can write and run do-files and read regression output, with graphs shown in the editor; for empirical research. Needs a licensed Stata 17+, the extension installed and the editor open. - [MCP Teams Server](https://hebbmind.com/ja/mcp/mcp-teams-server.md): [MCP] Microsoft Teams MCP open-sourced by Inditex: read messages in a set channel, start threads, reply and @mention members, and list members. Requires an Azure app registration and a Teams bot (usually with IT admin help); runs via Docker or Python 3.12 with uv. Next page: https://hebbmind.com/ja/tools.md?page=2&type=mcp&profession=algorithm%2Csupport%2Ceducation