Metadata-Version: 2.4
Name: gen-mcp-server
Version: 0.1.10
Summary: GEN MCP server — exposes the GEN platform (Auto Content Engine + agent chat) to MCP clients like Claude Code, Cursor, and VS Code.
Project-URL: Homepage, https://api.gen.pro
Project-URL: Repository, https://github.com/poweredbyGEN/gen-agentic
Author: GEN
License: MIT
Keywords: ai,content,gen,gen-pro,mcp,video
Requires-Python: >=3.10
Requires-Dist: fastmcp>=2.0.0
Requires-Dist: httpx>=0.27.0
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: respx>=0.21; extra == 'dev'
Description-Content-Type: text/markdown

# GEN — gen-mcp-server

<!-- mcp-name: io.github.poweredbyGEN/gen-mcp-server -->

**The all-in-one social content workflow as MCP tools** — analyze trends, generate content ideas, draft scripts, create the video, and publish, from your AI client (Claude Code, Cursor, VS Code). The official MCP server for the [GEN](https://gen.pro) platform.

One server covers the entire loop, so an agent can go from *"what's working in my niche?"* to a scheduled post without leaving the chat:

```
analyze    ideas         research      create         publish            automate
gen_ask    gen_generate  gen_research  gen_make_video gen_schedule_post  gen_create_recurring_job
           _content_ideas
```

## The workflow

**1. Analyze** — `gen_ask` answers questions about real social data from GEN's warehouse (TikTok, Instagram, YouTube + more): a video link's transcript & hooks, what's trending in a hashtag, an account's stats, rising sounds, comment sentiment.

**2. Ideate** — `gen_generate_content_ideas` produces data-driven content ideas tuned to your niche; `gen_research` digs into trends, top creators, and cross-platform/web signal for a topic.

**3. Create** — `gen_make_video` plans + scripts + renders a finished multi-scene video from a brief. For single pieces: `gen_create_image` (incl. Nano Banana Pro), `gen_create_video` (one clip — Veo / Kling / Sora / Seedance), `gen_create_song`, voice (`gen_design_voice`), B-roll import, captions, and `gen_render_video` to composite. Open-ended/multi-step goals go to `gen_chat`.

**4. Publish** — `gen_schedule_post` to TikTok, Instagram, YouTube, and X; connect accounts via `gen_get_social_connect_url`.

**5. Automate** — `gen_create_recurring_job` runs the whole loop on a schedule (research → create → publish) unattended.

## Quick start

```bash
pip install gen-mcp-server      # or: uvx gen-mcp-server
```

```bash
claude mcp add GEN --env GEN_API_KEY=your-pat -- gen-mcp-server
```

Cursor / VS Code: add a stdio server running `gen-mcp-server` with `GEN_API_KEY` set.

Get a Personal Access Token at **[gen.pro](https://gen.pro)** → log in → pick an agent → **API** page → Create API Key.

## Architecture

- **Transport:** stdio. **Auth:** `GEN_API_KEY` (Personal Access Token).
- **`gen_ask`** — natural-language questions about social data (front door; no raw scrape API).
- **`gen_chat`** — delegate multi-step build goals to the GEN composer.
- **~60 deterministic `gen_*` tools** for exact single actions (create image/video/song, render, schedule, manage assets/voices/credits).
- Resources (`gen://mental-model`, recipes) teach the model how to combine them.

## Environment

| Var | Required | Default |
| --- | --- | --- |
| `GEN_API_KEY` | yes | — |
| `GEN_API_BASE_URL` | no | `https://api.gen.pro/v1` |
| `GEN_AGENT_API_URL` | no | `https://agent.gen.pro/v1` |
| `GEN_AGENT_CORE_API_URL` | no | `https://agent-core.gen.pro/v1` |

## Credits

GEN is credit-based: generation/voice/research cost credits; reads and CRUD are free. On empty balance, tools return `insufficient_credits` pointing to `gen_buy_credits`. Use `gen_estimate_job` to price a job first and `gen_get_credit_balance` to check.

---

Built by [GEN](https://gen.pro) · [API docs](https://api.gen.pro) · auto-updates from PyPI on launch
