Mographr MCP server — render animated motion-graphics overlays (lower thirds, titles, callouts) as MP4 from Claude, Cursor or ChatGPT. Free, no API key.
git clone https://github.com/kossik/mographr-mcp-docs{
"mcpServers": {
"mographr-mcp-docs": {
"command": "node",
"args": ["/path/to/mographr-mcp-docs/dist/index.js"]
}
}
}Resumen de MCP Servers
# Mographr MCP Server
[](https://smithery.ai/servers/kossik/mographr)
Render real motion-graphics overlays — animated lower thirds, titles, callouts — from an AI assistant, and get back a finished MP4. Free, anonymous, no API key.
```
Endpoint https://mcp.mographr.com/mcp
Transport Streamable HTTP (stateless, JSON responses)
Auth None
Cost Free — watermarked MP4
```
Full documentation: **https://www.mographr.com/mcp** · Machine-readable: [`/mcp.md`](https://www.mographr.com/mcp.md)
---
## What this is — and what it isn't
This is **not** a text-to-video model. It does not invent footage.
It renders a small catalogue of hand-built motion-graphics templates with *your* text, *your* colour scheme and *your* choice of design, and returns a real MP4 you composite over your own video.
That distinction is the point. A diffusion model asked for "a lower third that says Dr. Maya Chen" produces something that looks like a lower third and spells the name wrong. This renders actual text in an actual font on an actual keyframed animation — legible at 1080p, identical on every run, safe to put in front of a client.
| | Mographr MCP | Text-to-video MCP servers |
|---|---|---|
| Output | Designed overlay, exact text | Generated footage, approximate text |
| Determinism | Same input → same file | Different every run |
| Typography | Real fonts, real kerning | Hallucinated letterforms |
| Auth | None | Account + credits |
| Use | Composite over your footage | Standalone clip |
---
## Install
### Claude Code
```bash
claude mcp add --transport http mographr https://mcp.mographr.com/mcp
```
### Claude Desktop
Settings → Connectors → Add custom connector → `https://mcp.mographr.com/mcp`
Older builds without that UI, in `claude_desktop_config.json`:
```json
{
"mcpServers": {
"mographr": {
"command": "npx",
"args": ["-y", "mcp-remote@latest", "https://mcp.mographr.com/mcp"]
}
}
}
```
### Cursor
`~/.cursor/mcp.json`, or `.cursor/mcp.json` in a project:
```json
{
"mcpServers": {
"mographr": { "type": "http", "url": "https://mcp.mographr.com/mcp" }
}
}
```
### VS Code
`.vscode/mcp.json`:
```json
{
"servers": {
"mographr": { "type": "http", "url": "https://mcp.mographr.com/mcp" }
}
}
```
### Anything else
Plain HTTP POST — no SDK required:
```bash
curl -sS https://mcp.mographr.com/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
```
> **Gotcha:** the `Accept` header must list **both** `application/json` and `text/event-stream`. The Streamable HTTP transport rejects the request otherwise. This trips up almost every hand-rolled client.
---
## Tools
| Tool | What it does |
|---|---|
| `list_motion_tools` | The catalogue. No arguments. Start here. |
| `get_motion_tool` | One tool's schema: field keys with max lengths and examples, design variants (each with its own canvas — some are vertical 9:16), colour schemes, and a ready-to-copy example call. |
| `render_motion_tool` | Queues a render, returns a `renderId` immediately. Repeating a call with identical parameters returns the cached result instead of re-rendering. |
| `get_motion_render` | Poll the `renderId` until `status` is `completed`, then read `downloadUrl`. |
### Worked example
```jsonc
// 1. what is available
{"jsonrpc":"2.0","id":1,"method":"tools/call",
"params":{"name":"list_motion_tools","arguments":{}}}
// 2. render one
{"jsonrpc":"2.0","id":2,"method":"tools/call",
"params":{"name":"render_motion_tool","arguments":{
"slug":"lower-thirds",
"fields":{"title":"Dr. Maya Chen","subtitle":"Marine Biologist"}}}}
// → { "renderId": "…", "status": "queued", "etaSeconds": 68 }
// 3. poll until completed
{"jsonrpc":"2.0","id":3,"method":"tools/call",
"params":{"name":"get_motion_render","arguments":{"renderId":"…"}}}
// → { "status": "completed", "downloadUrl": "https://…/tool-….mp4" }
```
A render takes roughly 30–70 seconds on the CPU lane.
---
## Limits
- About **8 renders per hour per IP**, and at most 6 queued at once across all MCP callers.
- Hitting a limit is **not** an error response. The tool returns a normal result with `status: "rate_limited"`, how many seconds to wait, and a link to the interactive page, which has no limit.
- Free renders carry a small mographr.com watermark.
- Image upload (avatars) is only available on the interactive page, not over MCP.
- Paid exports in the Mographr studio always take priority on the render lane, so free traffic never slows a paying customer down — and never gets starved out either, it just queues.
---
## Notes
- **Stateless.** No sessions, no session-id header, nothing to clean up. Every POST is independent, so a redeploy can never strand your connection. `GET` and `DELETE` on the endpoint return `405` by design. CORS is open.
- **Legacy host.** The endpoint is also reachable at `https://bff.mographr.com/mcp` — same server, and it will keep working.
- **REST too.** `GET https://bff.mographr.com/tools` lists the catalogue and `POST /tools/<slug>/render` starts a render. REST additionally supports image upload, which MCP does not.
## Links
- [Documentation](https://www.mographr.com/mcp)
- [Free tools with an interactive editor](https://www.mographr.com/tools)
- [Free motion graphics templates](https://www.mographr.com/motion-graphics-templates)
- [Pricing](https://www.mographr.com/pricing)
- [Site guide for agents (llms.txt)](https://www.mographr.com/llms.txt)
## Listed on
- [Official MCP Registry](https://registry.modelcontextprotocol.io/v0/servers?search=com.mographr) — `com.mographr/motion-tools`
- [Smithery](https://smithery.ai/servers/kossik/mographr)
## License
Documentation in this repository is MIT. The service itself is operated by Mographr under its [Terms of Use](https://www.mographr.com/terms); rendered output is subject to those terms.
Lo que la gente pregunta sobre mographr-mcp-docs
¿Qué es kossik/mographr-mcp-docs?
+
kossik/mographr-mcp-docs es mcp servers para el ecosistema de Claude AI. Mographr MCP server — render animated motion-graphics overlays (lower thirds, titles, callouts) as MP4 from Claude, Cursor or ChatGPT. Free, no API key. Tiene 0 estrellas en GitHub y se actualizó por última vez today.
¿Cómo se instala mographr-mcp-docs?
+
Puedes instalar mographr-mcp-docs clonando el repositorio (https://github.com/kossik/mographr-mcp-docs) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar kossik/mographr-mcp-docs?
+
kossik/mographr-mcp-docs aún no ha sido auditado por nuestro agente de seguridad. Revisa el repositorio original en GitHub antes de usarlo en producción.
¿Quién mantiene kossik/mographr-mcp-docs?
+
kossik/mographr-mcp-docs es mantenido por kossik. La última actividad registrada en GitHub es de today, con 0 issues abiertos.
¿Hay alternativas a mographr-mcp-docs?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega mographr-mcp-docs en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/kossik-mographr-mcp-docs)<a href="https://claudewave.com/repo/kossik-mographr-mcp-docs"><img src="https://claudewave.com/api/badge/kossik-mographr-mcp-docs" alt="Featured on ClaudeWave: kossik/mographr-mcp-docs" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!