"Remote Web Search Tool with File Write Capability" matching MCP servers:

A Model Context Protocol server that provides a scratchpad tool for LLMs to organize thoughts, take notes, and plan approaches to complex problems.

Enables AI assistants to read, search, and fully manage a Zotero library locally—organizing collections, editing items, uploading files, and managing notes, tags, and trash—through the local Zotero API without cloud sync.

An MCP server that lets an AI agent change what you can change in the Wispr Flow app: your personal dictionary, snippets, writing styles and polish instructions, custom transforms, scratchpad notes, todos, meeting titles and notes, and your profile name.

Turns your PDFs into locally stored flashcards and quizzes, grades your answers, and schedules spaced-repetition reviews entirely on your machine.

Enables AI clients to read and edit a self-hosted wiki as each member’s own account, with mandatory OAuth 2.1 or bearer-token authentication, scoped write/delete permissions, encrypted pre-change snapshots, and safe page/comment operations.

Enables a language model to access D&D 5e rules, reference data, and campaign state through MCP, with tools for dice rolls, encounters, lookups, and persistent notes.

Provides hybrid search (BM25 + vector) and staleness reporting for local markdown notes, exposing search and indexing tools to AI assistants via MCP.

Enables AI agents to search, read, and safely edit a single folder of Markdown notes over HTTPS, with fast full-text search, conflict-guarded edits, link-preserving moves, and a trash folder with restore. It runs self-hosted in Docker next to the notes and keeps strict boundaries around the mounted vault.

Provides ranked full-text search over Obsidian vaults using SQLite FTS5, BM25 scoring, and multilingual stemming, adding a vault_fts_search tool to find relevant notes beyond exact line matches.

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 remote MCP server that enables read/write access to a self-hosted Obsidian vault, exposing tools for reading, writing, patching, listing, and searching vault content. It works without Obsidian running and uses Git as a rollback mechanism.

Exposes the official Anytype MCP server (which only speaks stdio) as a remote Streamable HTTP endpoint, enabling Claude mobile/web to connect securely via bearer-token auth and Tailscale Funnel.

Enables remote access to Obsidian vaults from Claude.ai and Claude Code without needing Obsidian running, supporting multiple vaults with OAuth 2.1 and static token authentication. Provides note management tools like read, create, edit, delete, and search.

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.

This MCP server enables AI tools to read Dedao Brain (formerly Get Notes) web notes from a free account, exposing AI summaries, original transcripts, and audio attachment links or downloads, with an accompanying CLI.

Self-hosted MCP server that provides remote AI clients with read and write access to Obsidian vaults over HTTPS without needing the Obsidian desktop app running.

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

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.

Persistent docs and memory for AI agents. Writespace is a collaborative markdown editor with a built-in MCP server — your model reads, writes, organizes, and searches a shared workspace while humans edit the same docs live. Drop the ranked full-text search straight in as RAG retrieval.