"Material Design Icons" matching MCP servers:

Converts documents, web pages, media, and more to Markdown via an MCP server with tools for conversion, inspection, vault capture, and format listing, all running locally with privacy-first design.

Enables AI chat clients to search, create, and edit notes, manage decks and cards, preview card HTML/CSS, design your cards and work with media and .apkg deck packages through AnkiConnect.

Enables users to create and control portable, user-owned memory archives, including saving memories, reflections, values, and stories, exporting them as open JSON, publishing or discovering public archives, and loading consented material as a clearly-labelled memory-based AI persona.

Enables uploading images and files to Notion pages from Cursor chat, supporting multiple attachment types like image blocks, file blocks, cover images, and icons.

Enables Claude to search your team's design and issue comment threads from Figma, Jira, and Notion, answer questions with citations, surface feedback relevant to the code you're editing, and post replies or close threads after your confirmation.

Lets many Claude sessions on a LAN or VPN search, read, and contribute to one shared Obsidian-format Markdown wiki, with contributions queued in an inbox rather than editing the wiki directly. A separate locked-down nightly curator run is the only writer that merges inbox material into the vault.

Lets AI agents retrieve source-linked passages from a local folder of Markdown notes or an Obsidian vault, optionally following the explicit links between notes, and can also fetch passages from pinned public GitHub files you configure. It returns bounded evidence packets with original text, file paths and hashes so agents can answer from your material rather than generating content themselves.

Enables AI clients to inspect and make targeted, revision-checked edits to Excalidraw class diagrams stored in a local Obsidian vault, including adding, moving, rewiring, resizing, and deleting shapes, text, and arrows. It supports low-level design review by summarizing classes and relationships, and confines access to a configured folder while backing up drawings before each change.

Connects AI agents to a Notion workspace with token-based authentication, letting them create and edit pages, query databases, append blocks, apply templates, comment, and upload or read files through plain-language requests. Its three-tool, context-efficient design and built-in batched, idempotent operations support headless automation in CI, cron jobs, and self-hosted agents.

Enables Claude Code to use local markdown notes as persistent, searchable memory with hybrid recall, episodic memory, note-graph traversal, design memory, and optional cloud sync.

Enables MCP clients to search and read a local library of saved prompts, skills, MCP servers, and design boards, fill prompt blanks, and retrieve board design briefs through read-only, offline tools, prompts, and resources.

Enables AI coding agents to search a shared, sourced corpus of past Claude Code and Codex sessions and curated notes, retrieve full conversations and timelines, and write or extend memory in either a committed or confidential, git-ignored layer. Confidential material is withheld from results unless explicitly requested.

Enables Claude to access and update a team's design knowledge stored in a local Markdown folder, including searching decisions and recording new conventions.

Serves a unified local memory bank over a stdio MCP server, exposing five tools and one resource so any MCP-capable harness can list, search, and read memories imported from Claude Code, Codex, Cursor, Kimi Code, and ZCode. It gives agents a single read-only view of user preferences, feedback, project state, and reference material stored as plain Markdown files.

Enables other agents to search confirmed project knowledge, ingest source material, submit evidence-backed candidate memories, compile wiki content, and resume persistent conversations through shared local sessions and recall without duplicating the database.

An MCP server for saving project notes and design decisions to a SQLite database, with git-tracked storage and support for categories, tags, and search.

Enables AI assistants to read, search, create, and update Microsoft OneNote Desktop notebooks, sections, and pages on Windows using a dual-engine design that combines local .one backup parsing for offline full-text search with live COM automation for real-time authoring. Converts semantic HTML into native OneNote XML with rich typography, hierarchical sub-bullets, and grid tables — no cloud tokens, Graph registrations, or Azure credentials required.