xNotepad AI

com.xnotepadaiPublished by xnotepadai.comOfficial publisherv3.0.0Updated Oct 24, 2026

Create, search, and update notes in an xNotepad AI notebook, with semantic search and AI Q&A.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Remote MCP server that lets an assistant create, search, tag, link and query notes in a single xNotepad AI notebook as persistent memory.

What you can do
  • Create, list, read, update, delete and archive notes in the notebook
  • Search notes semantically and ask questions answered by AI from note content
  • Organize notes with tags, wiki-style links, merges and version history
  • Vectorize notes to enable semantic search
When to use it
Useful when you want an assistant to keep research, decisions or architecture notes between sessions, retrieve past decisions from your own notes, or hand notes from one agent to another in multi-agent workflows.
Requirements
A remote Streamable HTTP endpoint; no local runtime or package. Requires an xNotepad AI account and a bearer token sent in the Authorization header, obtained from the account settings page. Network access is required; a free tier allows 1,000 calls per month.
Before you install
The bearer token grants access to one notebook, so treat it as a secret and revoke it if exposed. The assistant can write, update, delete, merge and archive notes, though it is limited to notes tagged agent-created. Notes are encrypted client-side, but the server works on unencrypted copies synced by the user, and AI answers are generated by a third-party model service.

Installation

In SourceWeft

  1. Open xNotepad AI in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.xnotepadai%2Fnotes/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "xnotepad-ai": {
      "type": "http",
      "url": "https://www.xnotepadai.com/api/mcp/",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

xNotePadAI — MCP Server

A 13-tool MCP server that gives AI agents persistent, encrypted, searchable memory via notes.

Endpoint: https://www.xnotepadai.com/api/mcp/
Protocol: MCP (Model Context Protocol) JSON-RPC over Streamable HTTP
Auth: Bearer token
Free tier: 1,000 calls/month

Quick Start

json
{  "mcpServers": {    "xnotepad": {      "type": "http",      "url": "https://www.xnotepadai.com/api/mcp/",      "headers": {        "Authorization": "Bearer YOUR_TOKEN_HERE"      }    }  }}

Get your token: https://www.xnotepadai.com/settings/ → Your MCP Token (pre-generated, ready to copy)

Tools

ToolDescription
create_noteCreate a note (auto-tagged agent-created)
list_notesList all notes with titles, sizes, dates
get_noteGet full note content by ID
update_noteUpdate content (agent-created notes only)
delete_noteDelete a note (agent-created only)
search_notesSemantic search via vector embeddings
ask_notesAsk a question — AI answers from note content
get_versionsGet version history for a note
tag_noteAdd tags to a note
link_notesAdd [[wiki-links]] between notes
merge_notesMerge two notes (source deleted after)
archive_noteArchive a note
index_notesVectorise notes for semantic search

Security Model

  • Bearer token auth — SHA-256 hashed, stored in D1, revocable
  • Tenant isolation — tenant ID derived from token lookup, never from client args
  • Agent sandboxing — agents can only modify/delete notes tagged agent-created
  • Rate limiting — 30 req/min per IP
  • Zero-knowledge encryption — notes encrypted client-side with AES-256-GCM (MCP accesses unencrypted copies synced by the user)

Use Cases

  • AI memory — agents save research, decisions, architecture notes between sessions
  • Knowledge retrieval — "What did I decide about auth?" → searches your notes
  • Note automation — auto-tag, auto-link, merge duplicates, archive old notes
  • Multi-agent workflows — one agent writes, another reads later

Stack

  • Cloudflare Workers (runtime)
  • Cloudflare D1 (database)
  • Cloudflare Vectorize (semantic search)
  • Workers AI / Llama 3.3 70B (AI answers)

Docs

License

MIT

Source: mcp/README.md at commit dd50f68

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v3.0.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts