"Understanding the text content of a webpage" matching MCP servers:

Read and filter Excel, CSV, ODS, SQLite, Parquet and MTSV files — or a folder — as plain text

Enables MCP-compatible assistants to connect to a user's workspace, read across boards, notes, checklists, habits, money, meals, chores, and chat, and make scoped additions, changes, or removals with attribution.

Provides a bounded set of MCP tools for orchestrating research, content planning, visual production, approval gates, and immutable delivery of image-post projects.

An MCP server providing 8 content creation tools for case studies, newsletters, webinars, and more, based on the CRAFT Framework.

Runs 20 slash-command workflows across Google Calendar, Gmail, Linear, Slack, Granola, Google Docs, GitHub, Stripe, Notion, Google Forms, Sheets and Drive to produce morning briefs, meeting prep, action items assigned to owners and weekly updates. Reads proceed without asking, while anything that creates, sends, changes or deletes is shown for approval first.

Enables AI assistants to manage Microsoft Outlook Desktop (Classic) calendar and email through local COM automation, without Microsoft Graph or Entra registration.

Evaluates whether a meeting is worth attending, heavily weighted toward no, and provides time cost analysis, productivity impact, email viability score, and a polite decline template.

Enables AI-powered YouTube content management using Claude Code to orchestrate research, scripting, and scheduling via Google Sheets, Docs, and Drive.

Generates professional, modular welcome texts for new employees by extracting structured data from free-text input and assembling customizable templates.

Connects any MCP client to a Nextcloud instance through official WebDAV and OCS APIs, enabling browsing, searching, uploading, downloading, copying, moving, and deleting files and folders, plus managing favorites, public links and user/group shares, and the trash bin. Authentication uses the browser-based Login Flow with a saved app password.

Enables AI-powered task management in OmniFocus with support for project reviews, planned dates, repeating tasks, custom perspectives, hierarchical subtasks, and advanced filtering. Perfect for Claude AI integration with comprehensive CRUD operations for tasks, projects, and folders.

Enables AI agents to send emails, create drafts in Gmail, and append content to Google Docs via standardized MCP tools.

Enables collaborative manuscript editing where an AI agent reads the page, proposes changes scored against the writer's voice, and waits for acceptance or rejection before any text is committed.

Enables an agent to read and manage calendars across Nextcloud, iCloud, Google and any CalDAV server, merging every account into one sorted view. Exposes tools for listing and searching events, finding free time, and creating, updating or deleting events, with secrets kept out of the config.

Enables AI assistants to interact with Microsoft 365 and Office services through the Microsoft Graph API, providing tools for email, calendar, files, Teams, SharePoint, and more with configurable permissions and output formats.

An MCP server that enables AI assistants to interact with Atlassian Jira and Confluence across Cloud and Server/Data Center environments. It supports tasks like searching and summarizing documentation, managing Jira issues, and creating content through natural language.

Enables interaction with table data in a Federated Wiki, supporting CSV, TSV, JSON, and markdown pipe tables, with CRUD operations via REST and MCP tools.

Enables task management through MCP tools, resources, and prompts, backed by a PostgreSQL database.

A self-hosted Model Context Protocol server for Microsoft To Do. The key problem this solves: the Microsoft Graph API silently omits user-created lists on personal accounts (GET /me/todo/lists only returns well-known lists like "Flagged Emails"). This server works around it with a local SQLite registry that tracks every list you create, so your lists always show up.

Enables filling uploaded document templates (DOCX/HWP/HWPX/PDF) with chatbot-generated content while preserving original formatting, tables, and images, and saving as files.

MCP server for reading and writing .docx files. Exposes four paginated tools so agents can batch-read document content and styles, write content, and union style definitions.

Open-source cross-device clipboard manager with a built-in MCP server. Search and retrieve clipboard history synced across all your devices, read OCR text extracted from copied images, and add new items to the clipboard.

Enables creating PDF documents (invoices, certificates, reports, etc.) from natural language descriptions, returning a shareable link to preview and edit the document.

Bridges the editing capabilities of an already-open DingTalk document in the browser to any MCP host via standard stdio, forwarding tools to the page's internal MCP server over a local WebSocket. Supports read/write operations through suggested edits, pairing-based security, and zero runtime dependencies.

Turns markdown the agent produced into a link that renders as a typeset, paginated document with tables, Mermaid and math. The document is encoded in the URL, so nothing is uploaded and no account is needed.

Enables adding inline, range-anchored comments to specific text fragments in Google Docs, overcoming the limitation that Google APIs cannot create anchored comments.

Enables retrieval of work records for a selected week via MCP, providing structured data for generating team weekly reports.

Enables AI clients to read and edit Overleaf projects through the official git bridge, with local staging of changes and conflict detection before publishing.

Kanban boards, sprints, tickets and a team wiki on laver.app. Versioned writes so concurrent agents get a 409 instead of overwriting each other.

A read-only Model Context Protocol server that connects MCP clients such as Claude Desktop, Claude Code, Cursor or VS Code to KanbanFlow, exposing the configured boards and the tasks assigned to a chosen person across all of them. It resolves board, column, swimlane, color, label and people ids to readable names, reports which boards or columns could not be fully loaded, and never modifies any board.