"Web search tools and methods that don't require API keys" 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.

Enables a family assistant to search documents, inspect, fill, edit, and sign files, manage scheduled work and runs, and perform web searches, with each tool gated by the caller's groups.

Enables deterministic calculations for AI API and subscription costs, meeting time zones, recurring schedules, and cron next-run previews, returning normalized inputs, units, assumptions, dated sources, and links to results.

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.

Provides task and project management tools for AI agents, including todo list management, prioritization frameworks like Eisenhower Matrix and RICE scoring, time estimation using PERT, daily standup generation, and sprint burndown calculation.

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.

Enables AI agents to authenticate to typst.app cloud projects, list/create/delete projects, and read, write, surgically edit, rename, or delete Yjs CRDT-backed text files and binary assets over the native WebSocket and REST/GraphQL protocol. It also syncs cloud content into a local workspace to return structured Typst compiler diagnostics, export PDFs, and capture preview screenshots.

MCP server for Microsoft Forms automation, enabling AI agents to inspect forms, resolve branching, validate and submit answers, upload files, and manage response links.

Enables AI agents to read conversations, send messages, and manage members in Microsoft Teams via the Teams Chat Service REST API.

Enables MCP clients to call Web Presentation platform capabilities through tools mapped to External API v1, using a dedicated async HTTP client for JSON, binary, OpenAPI, and job-waiting operations in a single-user stdio development setup.

MCP server for document conversion and processing, enabling AI assistants to handle various document formats.

MCP server that provides tools to control a server-owned Pomodoro timer, allowing focus, pause, resume, skip, reset, and stats operations.

Enables AI assistants to convert and process various document formats through an MCP server interface.

An MCP server that generates MCP servers. Give it an API definition - OpenAPI 3.0/3.1 or a Postman collection or extend an existing server - and it scaffolds a complete, runnable, ownable TypeScript or Python MCP server for that collection of APIs.

MCP server for accurately reading and writing Excel .xlsx files while preserving structure, styles, and formulas. Provides tools for inspecting, editing, and aggregating spreadsheet data, with optional LibreOffice recalculation.

Enables AI agents to read, write, and edit Office documents via LibreOffice with token-efficient design. Supports multiple formats including DOCX, XLSX, PPTX, and legacy formats through LibreOffice bridge.

Enables AI assistants to manage Tempo timesheets and perform write operations such as create, update, delete, submit, approve, reject, reopen, and recall, with user confirmation safeguards.

Enables AI clients to create and manage tasks via a local REST API by converting natural language into HTTP requests through the Model Context Protocol.

Provides a read-only MCP interface to Kaiten, letting an agent retrieve cards, spaces, boards, columns, lanes, discussions, checklists, tags, custom properties, sprints and time-tracking reports with paging, filtering and long-text continuation. It also lists card and comment attachments and downloads selected originals as local files, with hashes and safe unique names, for further agent analysis.

MCP server for Todoist API integration, allowing management of tasks, projects, sections, labels, and comments through natural language.