mcpField
L
Liftli

Liftli

Remote
liftli.aiSocial Media0Updated 2w ago

About Liftli

Liftli is a hosted content planning and writing service for people publishing on LinkedIn, X, and Substack. It builds strategy and drafts from a user’s work and writing voice; posts require approval before publishing or scheduling.

Key features

  1. 01Learn a voice from existing posts
  2. 02Find ideas from work and news
  3. 03Build a content strategy and drafts
  4. 04Critique drafts before review
  5. 05Publish or schedule approved posts

Use cases

  1. 01Develop LinkedIn post ideas from meeting notes
  2. 02Draft posts in a consistent writing voice
  3. 03Schedule approved posts to LinkedIn or X
  4. 04Plan and draft Substack issues and Notes

MCP support

Liftli provides a remote MCP server over Streamable HTTP at https://mcp.liftli.ai/mcp. Its tools cover content strategy, drafting, review, publishing, scheduling, and results analysis.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.liftli.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

Details

From the project README

Liftli MCP

The remote MCP server behind Liftli: a head of content for LinkedIn and X, inside the AI you already use.
Built by Oded Tsamir.

Website · Install · Tools · Free open-source skills · Developer docs

LinkedIn    X (Twitter)    Substack

What this repository is. Liftli is a hosted service. This repo holds its public documentation and the server.json that lists it in the Official MCP Registry as io.github.liftli-ai/liftli. The server code is not open source, and there is nothing to self-host. The open-source part of Liftli is liftli-ai/linkedin-agent-skills: 31 free, MIT-licensed LinkedIn skills that run on your own agent's model.

What it does

Liftli learns your writing voice from your own posts, finds post ideas in your real work (voice notes, meeting transcripts, GitHub activity, chats and the news), builds and remembers your strategy, drafts in your voice and critiques every draft before you see it. Approved posts are published or scheduled to LinkedIn (and X on the Business plan) through their official APIs. For Substack it plans and drafts newsletter issues and Notes; you publish those on Substack yourself.

Nothing publishes without your approval. No browser extension and no bots acting on your profile.

Install

The server is remote, served over HTTPS with MCP's Streamable HTTP transport. Nothing runs locally.

Connector URL:

https://mcp.liftli.ai/mcp

Claude Code

claude mcp add --scope user --transport http liftli https://mcp.liftli.ai/mcp
claude mcp login liftli

Claude (web and desktop): Customize (briefcase icon), then Connectors, then Add custom connector, and paste the URL above into "Remote MCP Server URL".

ChatGPT, Codex, Cursor, Grok and other clients: add a custom or remote MCP server with the same URL. Client-specific steps: liftli.ai/developers.

You sign in once (secure WorkOS login). The free plan needs no card.

Tools

24 tools, grouped by job. Ask your assistant in plain language; it picks the tool.

JobTools
Start and profilestrategist_briefing, onboard, save_profile, rewrite_profile
Strategy and craftsave_strategy, playbook (13 briefs: hooks, ideas, calendar, growth, narrative, engagement, repurposing, Substack growth and more)
Writingplan_post, plan_comment, critique, ready_to_post, save_post
Publishingconnect_account (LinkedIn, X, Google Calendar), approve_post, distribute (publish now, schedule, manage the queue)
Memory and ideasremember, recall, news_monitor
Resultslog_outcome, analyze_results
Mediamedia (generate, upload, attach, list)
Channels and accountchannel (Telegram; WhatsApp coming soon), contact_support, upgrade, dismiss_suggestion

The list above matches the live server's tools/list. You can check it without an account:

curl -s -X POST https://mcp.liftli.ai/mcp \
  -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

How it differs

Most tools cover one end of the job: a scheduler, or a writer. Liftli covers the whole pipeline: it decides what is worth saying from your real week, drafts it in your voice, pressure-tests the draft, and publishes or schedules it after you approve. It lives inside the AI assistant you already use, so capturing an idea, writing it and shipping it happen in one place, including from a voice note sent over Telegram.

Safety model

  • Publishing and scheduling use the platforms' official APIs, connected only when you link an account.
  • Every draft waits for your approval.
  • No browser extension and no automated actions on your profile.

Support

Open an issue here, or use the contact_support tool from inside your assistant.

License

The documentation in this repository is MIT-licensed. The Liftli service is proprietary and governed by the terms at liftli.ai.

Comments

Markdown supported

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.