"Web and deep search functionality" matching MCP servers:

Provides local web search (Baidu, Bing, 360, Sogou), page scraping to markdown, and image description via LM Studio vision models, all without external APIs and with disk caching.

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.

Enables async-first working practices by providing tools to draft decision docs, convert meetings to async artifacts, score status updates, and triage sync vs async tasks. It also offers reference tools for the Open and Async book's principles and coaching prompts.

Provides tools for reading, modifying, and analyzing Google Sheets, as well as searching and managing Google Drive spreadsheets with access control.

An MCP server that exposes Google Docs and Gmail capabilities to LLMs via SSE transport.

Gives Claude deep tool-level control over Microsoft Excel files (.xlsx, .xlsm, .csv, .tsv) with 164 tools across 24 modules for reading, writing, formatting, formulas, charts, data analysis, and more.

An MCP-compliant server that exposes Gmail and Google Docs as tools, enabling AI agents to draft, send, and manage emails, as well as create, read, and append to documents through natural language.

An MCP server for managing Tempo worklogs in Jira, allowing users to track time, retrieve logs, and perform bulk operations via natural language. It integrates with the Tempo API to support creating, editing, and deleting work entries through MCP-compatible clients like Claude and Cursor.

Enables evidence-grounded resume tailoring by generating ATS-readable LaTeX/PDF resumes from a user-curated experience bank, with every bullet traceable to evidence and inferred wording flagged for user approval.

Enables AI agents to read, write, and format Google Sheets using the Google Sheets API v4.

A local MCP server that exposes the Tocaro Web API as MCP tools, enabling users to search users and groups, manage todo lists and tasks, post messages, and create groups through natural language.

MCP server that provides read access to Microsoft Loop workspaces and pages by reusing your Loop web session, enabling listing, reading, and searching across Loop content without app registration.

Provides AI models with full access to Jira Cloud functionality, enabling issue management, project tracking, sprint planning, and agile board operations through the Jira REST API v3 and Agile API 1.0.

Full-featured Notion MCP server enabling deep page reading, block editing, snapshot/restore, file uploads, table manipulation, page restore, and destructive page copying.

Enables reading, editing, and creating Korean HWPX documents through python-hwpx library. Supports document creation, paragraph/table/image insertion, metadata management, and workspace-restricted file operations with automatic backup functionality.

Enables interaction with Grist documents, workspaces, and records via the Model Context Protocol. It supports comprehensive operations including SQL querying, schema management, and record CRUD functionality.

Enables AI agents to start and log pomodoro and deep work sessions, manage tasks, and query a permanent per-skill ledger of focus hours via MCP.

Enables LLM agents to search, browse folders, read emails as Markdown (including Teams meeting links), and create draft messages through the real Microsoft Outlook Web client driven by a Playwright browser bridge. Drafts are never sent automatically, letting users review and approve messages in Outlook before sending.

An MCP server that exposes Feishu/Lark capabilities as function tools to MCP-compatible agents like Hermes and Claude Desktop. It provides 57 tools for messaging, document management, calendar operations, and task management through both hand-written fallback tools and bridged OpenClaw SDK functionality.

Enables MCP clients to work on Mirva boards and canvases with the user's own account, including drawing, painting, arranging, capturing, and interacting with the agent through the same API the web app uses.