"How to read and write in Microsoft Word" matching MCP servers:

Enables Claude to write in your personal style by learning from your local documents. It provides statistical style context for natural language rewriting, all without any data leaving your machine.

Persistent memory and pattern learning for AI coding assistants via MCP.

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.

A local MCP server that lets LLM agents read EPUB books and PDF documents with outline-first navigation, precise node reads, and local SQLite persistence.

Enables semantic search of the KJV Bible and personal knowledge graph for scripture study, notes, prayers, and memory verses, all running locally with no cloud dependencies.

Turns GitHub repository history into a cited maintainer skill for coding agents, providing tools to collect evidence, query the knowledge graph, and inspect bundles.

Enables read-only access to a local Zotero Desktop library, providing search, recent items, metadata, tags, collections, PDF attachments, and full-text search through a browser UI or MCP endpoint.

Search reusable technical experience from AI agents, inspect evidence and limitations, and discover public agent Trust Passports through seven anonymous read-only MCP tools. Apache-2.0 integrations, examples and documentation connect to the separately governed hosted Remnant service. Agent OAuth and Candy are separate surfaces.

Turn Obsidian notes into agent-ready context, preview-only plans, and safe repo handoffs.

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.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Enables AI agents to record and query reasoning steps in SQLite, offloading trace data from the context window, with DAG support and persistent cross-session memory.

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

Enables ChatGPT to search and fetch approved local Markdown notes through a private, read-only connection, returning results with file names, line numbers, and source context.

Enables precise measurement of live HTTP and WebSocket services while maintaining an append-only, evidence-based ledger of claims that agents can query with explicit timestamps, staleness indicators, and instructions for re-verification.

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

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 Claude and ChatGPT to share a single study-progress database for interview prep, coursework, and spaced repetition, with per-user data isolation and server-side SM-2 scheduling for due reviews and study plans.

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

Enables researchers to turn property-history questions into reviewable evidence dossiers by gathering sources, tracing people and places, linking conclusions to supporting or opposing passages, and exporting portable backups.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.

Local-first MCP server that extracts structured knowledge from markdown notes into SQLite with full-text search, enabling AI coding tools to retrieve relevant context offline at zero cost.

MCP server that connects AI agents to Google NotebookLM, enabling natural language interaction with notebooks, including Q&A, source ingestion, and audio overview generation.

Enables local-first knowledge management for Codex, providing tools for guided discussions, contextual recall, review, and daily topics.

Builds a searchable memory bank from persona-specific PDF content and exposes it as an MCP tool for querying.

A privacy-first, local-first MCP server that provides 15 ADHD/second-brain tools for capturing, prioritizing, and resurfacing tasks with context from calendar, mail, and messages.

MCP server for the full Pāli Tipiṭaka — ~444,000 segments at parity with SuttaCentral (Sutta + Vinaya + Abhidhamma). Hybrid search, full-sutta fetch with cross-references, segment-aligned translation comparison, and Pāli word lookup. Offered as Dhamma Dāna.

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content

Self-improving, verifiable memory for AI coding agents. Learns how you work, stops repeating mistakes, models each project, recalls the right lesson at the right moment. Every memory is signed and tamper-evident. Local-first.