"Understanding and Building Probability Density Functions (PDF) Models" 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 ChatGPT to read your Skim PDF reader's active document, page image, live selection, and red-underlined passages in one call, then mark those underlines processed or delete them on request over an outbound-only Secure MCP Tunnel.

Enables AI agents to extract PDF text, search with PDF++ citations, access vault files, manage tags, and run Dataview queries in Obsidian via MCP.

Converts Markdown to styled PDFs using VS Code's markdown styling and Python's ReportLab, providing a simple note storage system with custom URI scheme.

Enables safe interaction with PDFs, including listing files, extracting highlights with exact text, reading annotations and page text, and viewing metadata, all restricted to configured directories.

A Model Context Protocol server for managing text notes, with resources (note:// URIs), tools (create_note), and prompts (summarize_notes).

Enables synchronization and management of FoundryVTT journal entries within a Notion Story Bible, including media export and conflict resolution tools. It provides a Model Context Protocol interface for LLMs to preview, apply, and monitor data mirroring between tabletop RPG platforms and digital databases.

Enables AI agents to store and retrieve project context, bugs, decisions, and session logs by reading and appending markdown files in a local Obsidian vault, without requiring any cloud services.

Enables an AI assistant to browse folders, search and read notes, create and edit them, and move notes between folders within an account. Runs locally through a supported MCP client and supports basic Markdown while refusing edits that would lose existing formatting.

MCP server for Ultrathink: save and search your knowledge base from Claude Desktop, Claude Code, and any MCP client.

A TypeScript-based MCP server that enables users to query financial news, stock data, and index information while managing text notes with creation and summarization capabilities.

Enables local MCP clients to list, read, write, and search notes in an Obsidian vault via an HTTP server running inside Obsidian.

Provides AI clients with per-project todo management and persistent context notes via MCP, enabling task tracking and resume summaries.

Enables AI agents and users to manage workspace files, monitor system metrics, take persistent notes, and retrieve weather data via MCP tools and resources.

Open-source mind maps and whiteboard your agent draws on live: 22 tools for mind maps, notes, shapes, tables, charts, connectors, comments and HTML/PDF export; boards are local files.

Enables read-only search and analysis of your local Zotero library, including full-text PDF retrieval with OCR fallback, annotations, and cross-item comparison for synthesis.

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.

Lets Claude read handwriting from Viwoods AiPaper Paper-app notebooks over adb, returning pages as images with optional handwriting search and PDF import. A folder allow/deny policy decides exactly which notebooks are visible, so nothing unshared exists as far as the client can tell.

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

Keeps your notes, decisions and projects in one folder on your own server, so your AI assistant picks up where the last chat ended. Reads and searches PDF, Word, Excel and mail as text; write policies per folder, a trash instead of delete.

Enables persistent memory for Claude Code sessions by recording observations and building knowledge graphs for cross-session learning and domain knowledge management.

Converts JSON/CSV Markdown content into interactive flashcard pages with multiple templates, PDF export, and voice support for language learning.

Enables a conversational workflow to read local PDFs, propose exact word-level passages, apply colored highlights, and inspect saved annotated copies, plus recolor or remove existing highlights. All PDF and image I/O stays confined to a single workspace directory, with fingerprint verification and atomic saves so originals are never overwritten.

MCP server for local knowledge management with Markdown and PDF indexing using SQLite FTS5.

Agent-facing MCP: PPT/PDF to lecture write-up to Notion layout. Tools and prompts, no model API.

A simple note-taking MCP server for recording and managing notes with AI models.

Enables AI agents to query a professional profile in real time through tools for experiences, skills, projects, summary, recommendations, and GitHub repositories. It also serves a bilingual landing page and generated resume PDF from the same profile data.

Enables an LLM session to read and annotate a PDF alongside you in KDE Okular, seeing the current document and page, the text under your mouse, and your existing highlights and notes, while also writing new highlights, deleting annotations, and navigating the viewer to a page.

This project implements a Model Context Protocol (MCP) server for connecting AI models with Obsidian knowledge bases. Through this server, AI models can directly access and manipulate Obsidian notes, including reading, creating, updating, and deleting notes, as well as managing folder structures.

Enables hosts and models to add notes and search them through two typed MCP tools backed by an in-memory notes list.