# 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 Data analysis or Research / Academia: 121 items. > - ML / AI: Model training, evaluation and LLM application development. > - Data analysis: Querying, statistical analysis, reporting and visualization. > - Research / Academia: Literature search and reviews, experimental data analysis, paper writing and submission. - [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. - [MCP Toolbox for Databases](https://hebbmind.com/ja/mcp/mcp-toolbox.md): [MCP] Google's open-source database MCP server with ready-made query and SQL tools for dozens of sources, including PostgreSQL, MySQL, BigQuery, Spanner and MongoDB. Define controlled custom queries in tools.yaml. - [Browser Use MCP](https://hebbmind.com/ja/mcp/browser-use-mcp.md): [MCP] Local MCP server built into Browser Use: lets agents navigate, click, type and extract page content, or hand multi-step tasks to the built-in browser agent. Bring your own OpenAI or Anthropic API key. - [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. - [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. - [Fetch MCP Server](https://hebbmind.com/ja/mcp/fetch.md): [MCP] Official MCP reference server that fetches web pages and converts them to Markdown for the model, reading long pages in chunks from a given offset. Zero config, but it can reach internal network addresses, so use it with care. - [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. - [OpenBB MCP Server](https://hebbmind.com/ja/mcp/openbb-finance-mcp-server.md): [MCP] Official OpenBB MCP server exposing the OpenBB Platform's equity, ETF, macroeconomic, crypto and news data to agents; enable only the tool categories you need to save context. Needs uv locally; some data sources need your own API keys. Not investment advice. - [PostHog MCP](https://hebbmind.com/ja/mcp/posthog-mcp.md): [MCP] PostHog's official hosted MCP: lets agents query product analytics with HogQL, manage feature flags and A/B experiments, and investigate errors and session replays. Sign in to PostHog to authorize; tool calls are free, though a few LLM-powered tools count toward AI usage. - [@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. - [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. - [Finance Toolkit MCP](https://hebbmind.com/ja/mcp/financetoolkit.md): [MCP] From the FinanceToolkit author: computes ratios, valuation, risk and macro indicators with 500+ transparent formulas, for company comparisons and first-pass due diligence. Hosted, no install; enter a Financial Modeling Prep key on first connect (free tier: US stocks, 5 years). Verify results. - [Exa MCP Server](https://hebbmind.com/ja/mcp/exa-mcp-server.md): [MCP] Gives agents Exa web search and page content fetching, with an optional multi-step research agent and advanced filtered search. Maintained by Exa; the hosted service works anonymously with limits, and signing in or adding an API key raises them. - [mcp-obsidian](https://hebbmind.com/ja/mcp/mcp-obsidian.md): [MCP] Uses Obsidian's community Local REST API plugin so agents can list, read, search, append to and delete notes, and insert content at a heading, block reference or frontmatter field. Install that plugin and configure its API key first. - [Basic Memory](https://hebbmind.com/ja/mcp/basic-memory.md): [MCP] Stores agent memory as local Markdown notes that both people and AI can read, write, search and link, and you can open them directly in Obsidian. Local-first, open source and free, with a paid cloud sync option. - [AntV MCP Server Chart](https://hebbmind.com/ja/mcp/mcp-server-chart.md): [MCP] Generates 26+ chart types with AntV, including line, bar, Sankey, word cloud, mind map and pivot table, returning image links. Officially maintained by Ant Group's AntV team; uses a public rendering service by default and can be self-hosted. - [Excel MCP Server](https://hebbmind.com/ja/mcp/excel-mcp-server.md): [MCP] Create, read and modify xlsx workbooks without Microsoft Excel installed: formulas, formatting and conditional formatting, charts, pivot tables and tables. Runs locally over stdio or as a remote HTTP service. - [DBHub](https://hebbmind.com/ja/mcp/dbhub.md): [MCP] One server connecting PostgreSQL, MySQL, MariaDB, SQL Server, Oracle and SQLite, exposing just two tools by default to save context, with read-only mode and SSH tunneling. From Bytebase. - [Google Analytics MCP Server](https://hebbmind.com/ja/mcp/google-analytics-mcp.md): [MCP] Query Google Analytics 4 in natural language: read account and property info and run standard, funnel and realtime reports. Official from Google Analytics (experimental); requires Google Cloud Application Default Credentials. - [GeoAI MCP Server](https://hebbmind.com/ja/mcp/geoai-mcp-server.md): [MCP] MCP server from the opengeos GeoAI project: segment buildings, roads and vegetation in satellite imagery from text prompts, detect vehicles and ships, spot changes between images, estimate canopy height and fetch NAIP, Sentinel-2 and Landsat imagery. Install from the repo (Python 3.10+). - [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. - [Markdownify MCP Server](https://hebbmind.com/ja/mcp/markdownify-mcp.md): [MCP] Converts PDF, Word, Excel, PowerPoint, images, audio, web pages and YouTube transcripts into Markdown that agents can read and cite. Built on Microsoft MarkItDown; the Docker image lacks audio transcription and image recognition, so build locally for full features. - [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. - [EdgarTools](https://hebbmind.com/ja/mcp/edgartools.md): [MCP] Python library with a built-in MCP server for US SEC EDGAR data: search 10-K, 10-Q, 8-K and other filings and read XBRL-standardized financial statements, Form 4 insider trades and 13F holdings. Free with no API key; just set an EDGAR_IDENTITY. - [Korean Law MCP](https://hebbmind.com/ja/mcp/korean-law-mcp.md): [MCP] Searches Korean statutes, case law, administrative rules and local ordinances via the Korean Ministry of Government Legislation's Open API, verifies whether cited provisions and cases exist, and compares versions over time. Needs a free API key and Node.js; have a lawyer review results. - [Bright Data MCP](https://hebbmind.com/ja/mcp/brightdata-mcp.md): [MCP] Bright Data's official MCP: web search (Google, Bing, Yandex), any page to Markdown, structured data extraction from e-commerce, social and other platforms, and remote browser control. Needs an API token; includes 5,000 free requests a month. - [Perplexity API Platform MCP Server](https://hebbmind.com/ja/mcp/modelcontextprotocol.md): [MCP] Perplexity's official MCP with four tools: web search, grounded Q&A, deep research and reasoning, available remotely or run locally. Requires a Perplexity 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. - [Open-WebSearch](https://hebbmind.com/ja/mcp/open-websearch.md): [MCP] Multi-engine web search MCP with no API key, supporting Bing, DuckDuckGo, Brave, Baidu, Sogou, CSDN, Juejin and more; also fetches page content, CSDN articles and GitHub READMEs. Ships a CLI and a local server too. - [ToolUniverse](https://hebbmind.com/ja/mcp/tooluniverse.md): [MCP] From Harvard Medical School's Zitnik Lab: one MCP connecting 1,000+ scientific tools and databases for drugs and targets, genes and proteins, clinical trials, FDA data and PubMed, for biomedical and drug research. Runs with uv; some sources need API keys; medical conclusions need expert review. - [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+. - [DuckDuckGo Search MCP Server](https://hebbmind.com/ja/mcp/duckduckgo-mcp-server.md): [MCP] Web search through DuckDuckGo plus fetching and parsing page content, with built-in rate limiting and LLM-friendly result formatting. No API key needed; runs with a single uvx command. - [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. - [Brave Search MCP Server](https://hebbmind.com/ja/mcp/brave-search-mcp-server.md): [MCP] Brings the Brave Search API to agents: web, news, image, video and local business and place search, plus LLM-ready page context and AI summaries. Maintained by Brave; needs an API key. - [OpenContracts](https://hebbmind.com/ja/mcp/opencontracts.md): [MCP] Self-hosted open-source platform for contract and legal document analysis: detects cited laws and builds a citation graph, and its MCP server lets agents search the corpus, read texts and annotations, and follow citations. Deploy your own instance with Docker; have a lawyer review results. - [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. - [MySQL MCP Server](https://hebbmind.com/ja/mcp/mysql-mcp-server.md): [MCP] Gives agents controlled access to MySQL: list databases and tables, inspect schemas and sample data, and run SQL, with multi-database mode, SSL and SSH tunnels. Configure your own database user, ideally with least privilege. - [Mirobody](https://hebbmind.com/ja/mcp/mirobody.md): [MCP] Self-hosted engine that maps lab results, checkup reports and wearable data to standard metrics so agents can chart trends, citing the source file for every number. uvx mirobody mcp gives the coding tools; full records need Docker and an LLM API key. A doctor should review results. - [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. - [SearXNG MCP Server](https://hebbmind.com/ja/mcp/mcp-searxng.md): [MCP] Web search and page reading for agents through a self-hosted or trusted SearXNG metasearch instance, with no paid search API key. Requires a SearXNG instance with JSON output enabled. Next page: https://hebbmind.com/ja/tools.md?page=2&type=mcp&profession=algorithm%2Cdata%2Cresearch