"Fetch - Understanding its Meaning or Uses" matching MCP servers:

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

Enables interaction with Cubox through its CLI, allowing agents to manage bookmarks, highlights, and annotations via a single pass-through tool.

Enables AI agents to read and write a self-hosted AppFlowy instance, decoding its Yjs CRDT pages into Markdown.

Enables users to screen pasted job offers against a personal skills profile kept in local Markdown files, returning a fit verdict with evidence and deal-breakers while tallying missing skills into a recurring gap radar. It also tracks each offer through its application lifecycle and renders a one-page CV tailored to a specific offer from existing CV data, without scraping, network access, or its own AI.

Read-only access to your Gilbert meetings, transcripts and summaries over MCP — list, search, and fetch transcripts and summaries.

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.

An MCP server for TheBrain 15 that enables semantic search, graph traversal, and structured writing to a personal knowledge base via its local API. It provides tools to read and write thoughts, notes, links, and tags, with optional local embeddings for meaning-based search.

Exposes a Notion-synced AI OS as read-only MCP tools, enabling MCP-compatible AI clients to search the vault, fetch page contents, list projects, and check project statuses without scraping public links.

Enables users to fetch Zoom meeting summaries and write them into matching Obsidian 1:1 notes, with browser-based authentication and automatic session cookie management.

NoteDiscovery is a self-hosted plain-markdown notes app (MIT, no telemetry) with a built-in stdio MCP server. The server exposes tools so AI clients (Claude Desktop, Cursor, etc.) can search, read, create, edit, tag, and instantiate templates against the same vault the web UI uses.

Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes.

This MCP server enables AI assistants to perform calculations, fetch live weather, manage in-memory notes, access system info and note resources, and use reusable code review and summarization prompts.

MCP server for intelligent, use-adaptive Obsidian vault search. It uses Hebbian learning and graph centrality to rank files by usage and relevance.

Enables users to access local files, manage persistent notes via CRUD, fetch URLs, inspect system information, and analyze or transform text through MCP tools.

A small, readable MCP learning project implemented in TypeScript that uses a local JSON notebook to demonstrate core MCP features such as tools, resources, prompts, sampling, and notifications.

A multi-account MCP server for NotebookLM that maintains sticky account and notebook per session. It uses the internal RPC to avoid logout issues and adds tools for account switching, notebook selection, and health checks.

Local MCP server that automates an open Obsidian vault through Obsidian's official CLI, offering tools for note creation/update, search, tasks, daily notes, and organization. It uses MCP over STDIO, requires no cloud services, and provides safety/audit features for autonomous writes.

Enables users to connect their own account to AI clients to list notebooks and sources, fetch complete indexed source text and summaries, and ask grounded questions that return citation-to-source mappings, without creating, renaming, uploading, sharing, or deleting content.

Enables MCP clients to search, read, write, and organize pages, spaces, comments, attachments, labels, and member access in self-hosted Docmost Community Edition wikis via its internal HTTP API, using Markdown for page and comment bodies.

Connects AI assistants to a self-hosted Linkding bookmark manager through its REST API, enabling bookmark, tag, bundle, asset, and profile operations with confirm-gated writes and dry-run previews.