"The concept of thinking or introspection" matching MCP servers:

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.

Facilitates structured, progressive thinking through defined cognitive stages (Problem Definition, Research, Analysis, Synthesis, Conclusion), enabling users to break down complex problems, track thought progression, and generate summaries of their thinking process.

This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

An MCP server for navigating thought processes using branches, supporting thought cross-references and priority tracking to enhance insight generation and structured idea exploration.

An MCP server for managing contextual data as markdown files with metadata, enabling agents to save, retrieve, search, and delete contexts using simple CRUD operations.

Enables AI agents to search and modify a personal knowledge base through OAuth-secured MCP tools, covering Obsidian vaults and Google Drive mirrors with semantic search, note read/write operations, audit logging, and eval-gated local classification.

Model-agnostic, agent-ready Obsidian MCP server with RBAC, SLSA provenance, and native search. 163 tools across 31 domains, multi-vault, pluggable embeddings.

Provides persistent local memory of Claude Code sessions with TODO management and searchable activity logs via MCP tools.

A fast, private, read-only search for your second brain or any folder of Markdown notes. Your AI agent finds the right note and the exact line, with the note, heading and date as the source.

Enables coding agents to use an Obsidian vault as long-term memory, with search, reading, and writing of notes, plus automatic capture of learnings that are propagated to MOCs, daily notes, and the knowledge index with git commits.

Enables AI clients to search, read, and analyze a local SQLite knowledge base built from the full public archives of people you follow, bookmark, or subscribe to, with tools for onboarding, querying, and topic tracking.

MCP server that lets agents create and update persistent concept maps via the NodeLand API, returning shareable URLs for humans to view, embed, and keep editing.

Provides read-only access to finished meeting transcripts for AI assistants like Claude Code or Codex, enabling them to answer questions or draft summaries based on the transcriptions.

Enables AI agents and MCP clients to browse Roomtone meeting notes, add YouTube or pasted-text sources, generate summaries, ask questions answered from transcripts, and retrieve raw transcript text. Recording itself stays in the Roomtone app, so the server only reads and adds to existing meetings.

Provides MCP tools to read, write, append, and edit prose sections of nodes, backed by an in-memory or substrate-direct (Urania) backend.

Reads the local SQLite cache of the Notion desktop app to enable fast, offline search and retrieval of Notion pages from Claude.

An MCP server that lets Claude Code recall the context of past conversations from any project on demand.

Enables local scanning of markdown note folders to assess them against Open Knowledge Format v0.2 and ISO frontmatter tiers (Bronze/Silver/Gold), with no content leaving the machine.

Enables deterministic, token-minimal multi-hop retrieval from a vault of [[wikilink]] notes via the Model Context Protocol, allowing LLMs to answer questions by following authored links without vector databases or LLM calls during retrieval.

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 local clipping of webpages and YouTube transcripts into Obsidian from an AI assistant, with Markdown preview and saving tools, no browser extension or API key required.

Builds a dynamic knowledge graph from your notes and uses LLM reasoning to discover blindspots, hidden cross-domain connections, track concept evolution, and spark creative inspiration.

MCP server that connects Claude Desktop to Obsidian vault via the Local REST API plugin, enabling search, read, write, and management of notes plus executing Obsidian commands.

Enables local inspection and comparison of Noteastic backups, and exports pages or notebooks as PDF and PNG via MCP tools.

Enables personal knowledge management through Claude Desktop, allowing users to capture thoughts, connect ideas, and reflect on thinking changes via natural conversation.

Enables publishing Markdown documents as shareable web pages with optional groups, passwords, expiry, and themes, plus management of documents, attachments, and notes through the PostMD API.

Exposes meeting transcripts to any MCP-capable AI client so it can list meetings, page through a single transcript, and search across all of them for a topic with exact timestamps. Speaker labels, emails, phone numbers, and paths are pseudonymized or redacted before anything crosses the protocol, and transcripts are read-only.

Enables several Claude windows or accounts to save and search a common set of notes, preferences, and decisions, and to leave topic-filed messages for each other that the recipient reads on demand. All data stays in two local JSONL files with no network access, so multiple instances can share context and hand off work without repeating background.

Enables a coding agent to sketch explanations step by step on a shared hand-drawn canvas beside the chat, highlighting parts as it talks and reading back anything the user draws or notes. Boards persist per chat and can be searched, saved, and exported as Excalidraw files or PNGs.

Enables MCP clients such as Grok Bot to create and join GifOS meetings, send in a visible note-taking bot that transcribes participants locally via Whisper, post chat content, and read back or save the transcript. Everything, including the browser, bot credentials, and transcripts, runs on the user's own machine with no GifOS account or API key.