"MCP servers that work without API keys" matching MCP servers:

MCP server that tracks what you are working on. Logs are stored locally as one markdown file per day on your Desktop.

Manages persistent work memories and context across AI tools, enabling structured storage, search, and retrieval of work content, tasks, and knowledge with session-based project organization.

Enables recording, querying, and summarizing daily work entries with tags using a local SQLite database. Supports work logging, search, timeline queries, tag management, and automated reminders for tracking daily tasks.

Unofficial Notion MCP server built on Notion's private API (token_v2 cookie). Gives LLM agents full read/write access to the entire workspace — no integration token and no per-page sharing.

A TypeScript-based MCP server that implements a simple notes system, providing resources for accessing notes via URIs, tools for creating notes, and prompts for generating summaries.

Enables AI clients to read, write, search, and manage files in an Obsidian vault via MCP over SSE, running standalone without the Obsidian desktop app.

Enables advanced todo list management and content organization using Notion's API, supporting features like creating databases, dynamic filtering, and collaborative task tracking.

Built-in MCP server that gives AI agents direct access to an Obsidian vault for reading, writing, searching notes, and executing commands.

AI assistant integration with Logseq knowledge graph: 21 tools to read, write, query, and search notes, enabling seamless interaction with your notes.

A bridge server that allows LLM tools to interact with an Obsidian vault through a local REST API, enabling file operations, note management, and metadata access through natural language.

Enables AI agents to read, create, update and delete any file in a mounted folder of markdown notes, patch individual headings, blocks or frontmatter keys, search by text or JsonLogic queries over frontmatter, tags and links, and stream note changes as events. Runs as a standalone container requiring no Obsidian installation and binds only to private networks such as Tailscale or WireGuard.

Exposes an Obsidian notes vault as MCP services, enabling AI assistants to search, read, create, update, and delete notes and folders.

Self-hosted MCP server that lets AI agents and MCP clients read and modify Milanote content — boards, notes, links, to-do lists with due dates, columns, labels, comments, sharing, trash and export — through the session of your own signed-in Google Chrome. Works over stdio or HTTP and speaks the same tool set as the accompanying REST API and Python client.

Enables natural-language semantic search over your own local files through an MCP server, fully offline without API keys or a server daemon, with optional LLM-grounded answers and exact file:line sources.

An MCP server that gives Claude direct access to your reMarkable tablet's notebooks, enabling document search, PDF rendering, handwriting transcription, and diagram conversion, all locally without API keys.

Transforms Kindle highlight exports into structured personal memory summaries saved to Notion. Parses HTML and text files to generate book insights including themes, key ideas, and actionable takeaways using the host model's context window without external AI API calls.

A simple, searchable Markdown-based MCP server for saving and retrieving work logs with two tools: save_worklog and search_worklogs.

A standalone Node MCP server that provides semantic search, knowledge graph, and vault editing over an Obsidian vault. It runs locally as a single stdio process without requiring an Obsidian plugin for core functionality.

An MCP server for Capacities API 2.0 that enables AI agents to discover, create, read, update, and delete objects, blocks, and daily notes with structured JSON or Markdown, using personal API tokens.

MCP server that connects AI tools to Microsoft OneNote for Business via the Microsoft Graph API, enabling listing, creating, and updating notebooks, sections, and pages.