도구

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.

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.

Official MCP reference server for reading, writing, editing, moving and searching local files within an allowlist of directories, adjustable at runtime through Roots. Handy for organizing documents from a desktop client.

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.

Gives agents the current time and IANA time zone conversion, detecting the system time zone automatically. No API key needed. Official MCP reference server, written in Python.

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.

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.

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.

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.

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.

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.

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.

Open-source Zapier alternative with a built-in MCP server: agents can build and test automations in plain language, manage tables, or call hundreds of apps like email, spreadsheets and chat. Use the cloud or self-host, enable the MCP server in settings and connect via OAuth.

Skyvern's official MCP: drives a browser with vision LLMs to complete multi-step tasks like filling forms, downloading files and web research. Connect to Skyvern Cloud (OAuth or API key), or self-host Skyvern and run it as a local process.

Continuously records your screen and audio locally, extracting on-screen text and transcribing speech, so agents can search pages, docs and meetings you saw and summarize your day. Data stays local. Needs screenpipe running: source is free for personal use, desktop app is a subscription.

Official MCP from the FunASR project: transcribes audio files locally with the SenseVoice model, supporting Mandarin, Cantonese, English, Japanese and Korean, with optional segment timestamps. Local inference needs no API key and audio stays on your machine. Docker image available.

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.

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.

Lets agents operate the Windows desktop directly: launch apps, switch windows, simulate keyboard and mouse, read UI elements and run PowerShell, without needing a vision model. Windows only.

Community-maintained MCP for Jira and Confluence: search with JQL/CQL and create or update issues, pages and comments. Supports both Cloud and Server/Data Center deployments; needs an API token or personal access token.

macOS screen capture, accessibility-tree inspection and native UI automation, served over MCP so agents can see the screen and click, type and operate menus. Requires macOS 15+ with Screen Recording and Accessibility permissions granted.

Notion's official self-hosted MCP: uses an integration token to search, read and write pages and data sources, and can read and edit pages as Markdown. Notion now recommends its hosted Remote Notion MCP, and this repo is no longer actively maintained.

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.

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.