About MarkIt
MarkIt is an MCP server that connects an AI client to a personal library of saved links, posts, and notes. It lets people search and read saved material, add items, and manage reminders through natural-language requests.
Key features
- 01Search saved items in plain language
- 02Fetch full content of an item
- 03Save links and text notes
- 04Create, list, and cancel reminders
- 05Filter searches by item metadata
Use cases
- 01Find a previously saved article or post
- 02Save a URL or note while working
- 03Set a reminder for a saved item
- 04Review saved material by category or date
MCP support
MarkIt exposes its library and reminder functions to MCP clients through a remote Streamable HTTP server. Connections use OAuth 2.1 or a personal API key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mark-it.co/api/mcpclaude mcp add --transport http fuzulsfriend-markit https://mark-it.co/api/mcp{"mcpServers":{"fuzulsfriend-markit":{"type":"http","url":"https://mark-it.co/api/mcp"}}}Open in Cursor{"servers":{"fuzulsfriend-markit":{"type":"http","url":"https://mark-it.co/api/mcp"}}}Open in VS Code{"mcpServers":{"fuzulsfriend-markit":{"type":"http","url":"https://mark-it.co/api/mcp"}}}{"mcpServers":{"fuzulsfriend-markit":{"serverUrl":"https://mark-it.co/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
8| Parameter | Type | Required | Description |
|---|---|---|---|
| sort | enum | No | relevance | date_desc | date_asc |
| tags | array | No | Any-of tag match |
| type | enum | No | url | image | note | document |
| limit | integer | No | |
| query | string | No | Natural-language topic, e.g. 'AI coding tools'. Omit for a newest-first date listing. |
| author | string | No | Author/creator name (case-insensitive substring) |
| dateTo | string | No | Inclusive ISO date |
| source | string | No | Platform key (instagram|tiktok|youtube|twitter|github|linkedin|facebook) or a domain substring |
| category | string | No | Category name - see list_categories for valid names |
| dateFrom | string | No | Inclusive ISO date, e.g. 2026-06-01 |
| likedOnly | boolean | No | |
| pinnedOnly | boolean | No | |
| excludeSource | string | No | Exclude a platform/domain (same format as source) |
Details
From the project README
MarkIt MCP - connect your AI to your library
Bring your own AI. MarkIt is the memory.
Tip
The lazy path (recommended): paste this repo's URL into your AI and say "connect me to MarkIt". It reads llms.txt and handles everything below for you.
MarkIt saves the links, posts, and notes you'd otherwise lose, and makes them searchable in plain language. This repo is the official guide for connecting your own AI - Claude, ChatGPT, Cursor, and friends - to your MarkIt library over the open Model Context Protocol.
Once connected, your AI can search your library, read what it finds, save new things into it, and set reminders. In your words, not keywords.
Server URL: https://mark-it.co/api/mcp
Transport: Streamable HTTP
Auth: OAuth 2.1 (sign in) or a personal API key (mkt_...)
Pick your path
Option 1 - Sign in (OAuth). No key to handle. Works with Claude, ChatGPT web and Claude Code only: MarkIt refuses sign-in from any other app, so a look-alike app cannot trick you into signing in.
Option 2 - API key. Generate a key in Settings > Integrations (shown once, keep it secret). For every other app: Cursor, VS Code, Codex CLI, Windsurf, Cline, Zed, scripts, and the ChatGPT desktop app.
Option 1 - sign in from your app
| App | Steps |
|---|---|
| Claude (claude.ai + Claude Desktop) | Settings > Connectors (under Customize) > Add custom connector > paste https://mark-it.co/api/mcp > Connect > sign in to MarkIt > Allow. Available on all plans (Free allows one custom connector). |
| ChatGPT (web) | chatgpt.com/plugins > + > Add custom MCP server. Icon: upload the MarkIt icon (optional, keeps the MarkIt logo in your plugin list instead of a puzzle piece). Name: MarkIt. Server URL: https://mark-it.co/api/mcp. Authentication: OAuth. Tick I understand and want to continue > Create as a plugin > sign in to MarkIt > Allow. |
| Claude Code | claude mcp add --transport http markit https://mark-it.co/api/mcp then run /mcp in a session and pick Authenticate. Add --scope user to use it in every project. |
Any other app: use Option 2.
Option 2 - use your API key
- In MarkIt Settings > Integrations, open Connect Your AI and generate your key. It starts with
mkt_and is shown once. - Grab your app's config from
clients/and replacemkt_your_key_here:
| App | Config |
|---|---|
| Claude Code | clients/claude-code.md |
| Cursor | clients/cursor.json |
| VS Code | clients/vscode.json |
| Codex CLI + ChatGPT desktop app | clients/codex.toml (they share ~/.codex/config.toml) |
| Windsurf | clients/windsurf.json |
| Cline | clients/cline.json |
| Zed | clients/zed.json |
| Anything stdio-only | clients/mcp-remote.json |
Rules of the key: one per account, treat it like a password, never paste it into a chat, revoke or regenerate anytime in Settings.
What your AI gets
| Tool | What it does |
|---|---|
search | Plain-language search over your library, with optional filters (category, platform, type, author, tags, dates). |
fetch | Full stored content of one item by id. |
list_categories | Your categories with item counts. |
save_item | Save a URL or a text note into your library. MarkIt scrapes, categorizes, and indexes it. Each save spends one monthly capture; re-saving a URL you already have is a free no-op. |
create_reminder | Set or reschedule a reminder on an item (email for everyone; WhatsApp/Telegram on Pro). |
list_reminders | Your pending reminders. |
cancel_reminder | Cancel one reminder by id. Never touches the item itself; Google-Calendar-synced reminders stay managed on-site. |
send_feedback | Send a short note straight to MarkIt's founder - only when you ask it to. A real person reads every one. Max 3 a day. |
What it can NOT do, by design: delete items, edit your account, touch anyone else's data. Saved page content is treated as data, never as instructions.
Privacy, in one breath
Your AI talks to MarkIt with your identity and only ever sees your items. Whatever AI you connect (Claude, ChatGPT, ...) is your own tool under its own terms - MarkIt does not send your library anywhere on its own. OAuth grants are revocable from your AI app; the API key is revocable in Settings. Full details: Privacy Policy.
Troubleshooting
- 401 right after connecting with a key: the header must be exactly
Authorization: Bearer mkt_...- check for a lost space or a truncated key (regenerating in Settings invalidates old keys). - Windsurf: the remote-server field is
serverUrl, noturl. - Cline: set
"type": "streamableHttp"explicitly. - VS Code says it cannot start the server: an entry with a
urlalso needs"type": "http". - Claude says "Authorization with MarkIt failed" right after you approve: retry once. If it fails again, use Claude Code (Option 1) or any app with an API key (Option 2). An older Anthropic-side bug caused this; claude.ai sign-in worked again in our test on 2026-10-21.
- "This app is not supported. Use an API key instead.": sign-in is limited to Claude, ChatGPT web and Claude Code. Use an API key (Option 2).
- Sign-in window never comes back: finish the login in the browser tab it opened, then retry from the app; some apps need a retry after the first authorize.
mcp-remoteshim: keep it current (mcp-remote@latest; versions before 0.1.16 have a known critical vulnerability). No space around the colon inAuthorization:${AUTH_HEADER}on Windows.- Still stuck? [email protected].
For your AI
Point your assistant at llms.txt - a plain-text playbook that teaches it to connect you and to use the tools well. Same file, branded URL: mark-it.co/mcp/llms.txt.
Claude Code users can go one step further: copy the skill/ folder into .claude/skills/markit/ and Claude picks up the full MarkIt usage playbook (when to search vs save, note etiquette, reminder handling) automatically.
License
MIT. The MarkIt name and logo belong to MarkIt.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.