Liftli for developers and AI agents

Liftli is a content strategist and social manager that installs as an MCP, not an app. It runs inside the AI you already use, so an agent can plan, draft, publish and schedule to LinkedIn, X and Substack from the same conversation the user already works in. This page is the front door: connect it, and the workflows it unlocks.

Start free — no card Read llms.txt

Maintained by Oded Tsamir, founder of Liftli · last reviewed July 2026

Connect Liftli (one MCP URL)

Liftli is a single remote MCP server. The URL is the same across every client:

Client	How to connect
Claude (desktop / web)	Customize (briefcase icon) → Connectors → Add custom connector → paste the Remote MCP Server URL `https://liftli-strategist-mcp.onrender.com/mcp`
Claude Code	One command: `claude mcp add --scope user --transport http liftli https://liftli-strategist-mcp.onrender.com/mcp`
ChatGPT (Developer Mode, beta)	Settings → Apps & Connectors → Developer mode → add `https://liftli-strategist-mcp.onrender.com/mcp`
Codex (beta)	In `~/.codex/config.toml`: `[mcp_servers.liftli]` with `url = "https://liftli-strategist-mcp.onrender.com/mcp"`, then `codex mcp login liftli`
Cursor (beta)	Settings → MCP → Add server → the same URL
Antigravity / other MCP clients	Add a remote (streamable-http) MCP server pointing at `https://liftli-strategist-mcp.onrender.com/mcp`

After connecting, the user signs in once with a secure WorkOS login. Liftli then extracts their writing voice and starts drafting in it. No tokens, no credits, no AI markup: it runs inside the user's existing AI subscription.

What an agent can do with Liftli

Liftli is not a fixed set of buttons. It is an agent surface, so the ceiling is what you can ask an agent to do. A few real workflows:

From a voice memo to a scheduled week. "Take my last voice note and draft and schedule five posts across LinkedIn and X." Liftli plans against the saved strategy, drafts in the user's voice, critiques each draft, and queues them behind one-tap approval.
From real work to post ideas. Point it at call transcripts, GitHub activity, or a chat, and it mines them for post "seeds" grounded in what actually happened, instead of a blank prompt box.
Compose with the user's other tools. Because it lives inside the assistant, you can pull ideas straight from the user's connected transcription or notes tool and hand them to Liftli in one step, no export, no dashboard.
Close the loop. After a post ships, Liftli scores who engaged into a ranked warm-lead list and recalibrates next week's plan on what worked.

Full capability list and the tool catalog are in llms.txt and the expanded llms-full.txt.

Free skills your agent can run locally

Separate from the MCP, all 28 of Liftli's free tools ship as installable skills. The agent's own model runs the distilled methodology locally, no account required:

Install all skills:

npx skills add liftli-ai/skills

One skill:

npx skills add liftli-ai/skills --skill linkedin-hook-generator

Browse all 28 at liftli.ai/skills, or read the machine-readable manifests: /.well-known/skills and /.well-known/agent-skills/index.json. Source: github.com/liftli-ai/skills.

Why agent-native, and why it is ban-safe

Most content tools are dashboards you open, or browser extensions that act on your logged-in session. LinkedIn's User Agreement prohibits scraping and extension-driven automation, and it enforces that. Liftli sits on the other side of that line: it publishes and schedules through the platforms' official APIs, connected only when the user explicitly links an account, and it never runs a bot action on a profile. Nothing publishes without the user's one-tap approval.

The agent-native shape is also the reason the tool inherits the user's context for free. It is already inside the assistant that holds the user's calls, code, and thinking. That is the layer where content ideas actually happen, and where an agent can carry them all the way to published.

Machine-readable resources

/llms.txt — concise index for LLMs: what Liftli is, install, capabilities, tools, pricing.
/llms-full.txt — the expanded single-file reference (capabilities, full skills catalog, glossary, FAQs).
/ai-agents.md — a short directive for an AI agent helping a user grow on LinkedIn, X or Substack.
/.well-known/skills and /.well-known/agent-skills/index.json — the skills manifests.
/sitemap.xml — every indexable page.

Frequently asked questions

How do I connect Liftli to Claude, ChatGPT or Cursor?

Liftli is a remote MCP server. In Claude, add a custom connector with the Remote MCP Server URL https://liftli-strategist-mcp.onrender.com/mcp. In Claude Code, run one command: claude mcp add --scope user --transport http liftli https://liftli-strategist-mcp.onrender.com/mcp. ChatGPT (Developer Mode), Codex, Cursor and Antigravity use the same URL. After connecting, the user signs in once with a secure WorkOS login, and Liftli learns their writing voice.

Is Liftli an API or an app?

Neither in the usual sense. Liftli is an MCP (Model Context Protocol) server that runs inside the AI assistant the user already uses. There is no dashboard to open and no separate app to context-switch into. The agent calls Liftli's tools in the same conversation where the user already works, so it inherits the user's real context instead of asking them to re-enter it.

What can an agent actually do with Liftli?

Everything a content team does, on request: build and remember a content strategy, mine the user's real work (voice notes, call transcripts, GitHub activity, chats, the news) for post ideas, draft in the user's extracted voice, run a plan to draft to critique to revise loop, publish and schedule to LinkedIn, X and Substack through official APIs, and score who engaged into a warm-lead list. Because it is an agent surface, you can also compose these with the user's other connected tools in one step.

Is it safe for the user's LinkedIn or X account?

Yes. Liftli never uses a browser extension, never scrapes, and never runs bot actions on the profile. Publishing and scheduling go through the platforms' official APIs, connected only when the user explicitly links an account, and nothing publishes without the user's one-tap approval. That is the ban-safe category by design.

Are the free tools and skills usable without connecting the MCP?

Yes. The 28 free tools at liftli.ai/tools run in the browser with no login. Every tool also ships as an installable skill your agent can run locally with npx skills add liftli-ai/skills. The skills are a distilled methodology your own model executes; the MCP is the full connected pipeline with the user's saved strategy and memory.