MCP server that converts PDF, video, web, and audio inputs into structured Markdown notes with support for checkpointing, batch processing, and Obsidian integration.
Enables forwarding Douyin or Bilibili video shares to Kimi for AI analysis and automatically writing the resulting Chinese notes into an Obsidian vault.
Enables automatic collection and AI analysis of Slack messages to create organized Notion pages, supporting custom analysis directions like meeting minutes, issue extraction, and topic classification.
Enables users to manage a personal to-do list backed by SQLite, adding single or multiple tasks, listing incomplete tasks, renaming or updating task status, and marking tasks complete. All state persists in a local database created automatically on first run.
Serves plain-text notes that an Obsidian user has explicitly published for AI over streamable HTTP, with full-text and embedding-based search. MCP clients can read and search those notes and queue suggested edits that the user's own client applies only if the AI rules allow it.
Automatically maintains a personal journal on behalf of an AI agent, storing text, photos, and voice notes as plain markdown files locally. Enables agents to add entries, recall memories, and reflect on patterns without user intervention.
A TypeScript-based MCP server that implements a simple notes system, allowing users to create, access, and generate summaries of text notes through Claude Desktop.
Self-hosted MCP server that provides embedding-powered semantic search with graph context over Obsidian vaults, supporting multiple vaults, local embeddings, and a web dashboard.
A zero-config personal knowledge management MCP server that enables Claude Desktop to automatically classify, search, and organize local Markdown notes using hybrid search and Graph RAG.
Enables converting PDF, EPUB, and TXT books into validated chapter analyses, guarded Obsidian notes, and installable Agent Skills that can be reused across Codex, Claude Code, or other MCP-capable clients.
Converts rough notes into a citation-grounded report, verifying each claim against source notes and handing off to SuperDocs with a faithfulness circuit breaker.
Provides read-only, agent-facing access to a private knowledge vault: full-text and hybrid search across pages, targeted reading of notes or specific sections, and listing of notes and projects, with results returned as compact masked markdown to keep context small. Every response is passed through a secret masker and calls are audited, so agents can retrieve only the content they need without exposing credentials.
Enables AI agents to run semantic search over local Obsidian or Markdown vaults, returning notes ranked by meaning with paths, headings, scores, and snippets, and to trigger incremental reindexing of changed notes. Everything runs on the user's own machine, so no note content leaves it.
Enables AI agents to use a Markdown notes folder as a knowledge base, with tools to list, read, search by keyword or meaning, and safely write notes guarded by content hashes.
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.
Enables personal knowledge management through Claude Desktop, allowing users to capture thoughts, connect ideas, and reflect on thinking changes via natural conversation.
Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes.
Enables MCP clients to search and read saved Karakeep pages and notes, save new bookmarks or notes, and organize them with tags and lists over stdio or authenticated remote HTTP.
Enables AI agents to work with a local Anki collection through MCP while Anki stays open in the background, listing and creating decks, listing note types, searching notes, and previewing or creating Basic and Cloze notes in batches. Deletion of cards or decks requires explicit confirmation in Anki and completes only after a recovery backup finishes.
Enables AI agents to search, retrieve, create, append, tag, import, bookmark, and organize notes and documents in a Keep It library through AppleScript.
A local MCP server that provides AI agents with persistent sticky-note memory, storing Markdown notes on disk and offering tools for creating, reading, updating, deleting, searching, and listing notes across sessions.
An MCP server that connects AI assistants to Notion, enabling automated research, GitHub tracking, and content pipelines with human-in-the-loop approval via a Notion task queue.
A Model Context Protocol implementation that enables AI assistants to interact with markdown documentation files, providing capabilities for document management, metadata handling, search, and documentation health analysis.
Enables local hybrid search over Obsidian and Markdown vaults via MCP, combining vector retrieval, full-text search, reranking, graph navigation, and safe CRUD while keeping data local.
Enables creating and managing text notes through MCP resources and tools. Provides note creation capabilities and automatic summarization of all stored notes.
Enables agents to read and write Markdown documents, HTML pages, data files, PDFs, screenshots, and videos through a standard remote MCP server with OAuth, per-agent revocable project permissions, version history, and stable artifact links.
Enables MCP-compatible agents to search and retrieve linked context from a local Obsidian-compatible Markdown vault, with read-only tools by default and optional tools to capture, update, link, organize, and index notes.
Enables local semantic and full-text search over Markdown notes through MCP, returning relevant passages ranked by meaning and exact terms without requiring a GPU or hosted APIs.
Enables people and their AI agents to share a kanban board whose tasks, hand-offs, reviews, notes and alerts live as markdown files in a private GitHub repo, with per-person access control. Works from Claude, ChatGPT, Claude Code, Codex or any MCP-speaking client, and can draw the board inside chats.
Enables AI agents to search and manage a local Markdown memory vault over stdio, including hybrid search, note retrieval and addition, session handoff claiming, and status checks without holding a model in memory.
Lets MCP clients search, read, create, append, replace, move, and batch-update local Markdown notes safely, with conflict detection via SHA-256 and optional managed update blocks, without requiring a vector database.
A self-hosted MCP server that collects links and articles from web and mobile, allowing AI agents like Claude or ChatGPT to read and analyze them as a reading list.
Exposes MCP tools for safely evaluating arithmetic expressions, retrieving current time in IANA time zones, and saving or listing bounded text notes for agents to call. It emphasizes input validation, controlled errors, and secure local note storage.
A lightweight MCP memory engine for AI coding agents that provides zero-token-waste memory recall, knowledge graph management, and Obsidian-compatible notes. It enables agents to persist and retrieve project decisions, inspect file structures efficiently, and manage a persistent knowledge graph without Python dependencies.
Enables any MCP-capable agent to maintain a shared .apm Markdown source of truth for project goals, tasks, decisions, handoffs, and health insights. It lets multiple agents and CLI/dashboard tools coordinate using the same file-based read/write logic without a database.
Local MCP servers for the Agent-Obsidian workflow, providing vault file I/O, todo management, and arXiv paper fetching with zero-dependency single-file Node.js scripts.
Enables AI agents to keep and query long-term memory of past conversations, with hybrid keyword-plus-semantic search, session, day, week, month and year summaries, saved notes, and a running set of current facts about the user. Exposes this over MCP streamable HTTP through five tools so any client can retrieve context that would otherwise be lost between sessions.
Enables AI agents to perform deep, read-only searches across a local work journal’s timeline cards, detailed write-ups, observations, and standups over arbitrary date ranges.
Lets coding agents like Codex, Cursor, and Claude Code share and resume each other's chats, and attach to a common task with saved notes that can be searched later. This keeps task state and decisions in sync no matter which agent you switch to.
A machine-local, agent-writable knowledge base MCP server that lets coding agents autonomously record and retrieve hard-won operational facts, incidents, and corrections as markdown pages in a git repo, with provenance, talk pages, and search.
Enables any MCP-capable coding agent to turn past session transcripts into durable, linked memory pages — verifying, correcting and reorganizing existing notes with transcript-quoted evidence — using the host's own model, with everything stored locally in the project's .dream folder. Users can run a "dream" to capture where work stands, roll back runs, and reload a short index at the start of the next session so context lost by compaction is not lost for good.
Enables creating structured Obsidian notes from text and transcripts, searching notes, generating meeting-summary prompts, and viewing note statistics, with guardrails against prompt injection and fidelity checks.
MCP server for the driaforall/mem-agent model that enables interaction with an obsidian-like memory system through apps like Claude Desktop or LM Studio.
Enables AI agents to read and write a local-first Markdown/Obsidian notebook via a single capture call that routes text into the right notebook, board, or daily journal entry and returns related notes, alongside search, note and card management, and numeric metric series. Access is governed by per-agent tokens with read/write/admin scopes, optional folder restrictions, and an audit log of every action.
Enables MCP clients such as Claude Code and Codex to share typed long-term memory (decisions, risks, handoffs, snapshots, notes, tasks) stored as one plain Markdown file per record in an Obsidian vault. Users can read, link and hand-correct that memory in Obsidian, with revision-checked updates, a handoff lifecycle, stemmed search and secret redaction.
Enables multi-agent developers to query a local, Git-backed Markdown/SQLite knowledge base through read-only tools for overview, hybrid full-text and semantic search, project context, mistakes and guardrails, and individual notes.