VideoReceiverMCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@VideoReceiverMCPlist all saved videos"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
VideoReceiverMCP
A minimal MCP (Model Context Protocol) server that receives video files over both:
stdio — for local agents (Claude Desktop, Cursor)
HTTP (Streamable-HTTP) — for remote/network clients
How it works
Sender project VideoReceiverMCP server
| |
| 1. encode video -> base64 string |
| 2. call receive_video(base64) -----> |
| | 3. decode base64 -> binary
| | 4. save to received_videos/
| <-- "Video received! ..." |MCP uses JSON-RPC (text only), so videos are base64-encoded before sending.
Setup (local)
# 1. Run the setup script (creates venv + installs deps)
.\setup.ps1
# 2. Activate venv
.\venv\Scripts\Activate.ps1Run locally
stdio mode (for Claude Desktop / Cursor)
python video_mcp_server.pyHTTP mode (test network transport locally)
python video_mcp_server.py --http
# MCP endpoint: http://localhost:8000/mcpConfigure in Claude Desktop
Edit %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"VideoReceiverMCP": {
"command": "C:/path/to/mcp/venv/Scripts/python.exe",
"args": ["C:/path/to/mcp/video_mcp_server.py"]
}
}
}Configure in Cursor / VS Code
Edit .cursor/mcp.json in your project:
{
"mcpServers": {
"VideoReceiverMCP": {
"command": "C:/path/to/mcp/venv/Scripts/python.exe",
"args": ["C:/path/to/mcp/video_mcp_server.py"]
}
}
}Deploy on Render (free, persistent server)
Why Render and not Netlify? Netlify runs serverless/stateless functions — they cannot keep a persistent connection open, which MCP Streamable-HTTP requires. Render's free tier runs a full persistent Python process.
Push this repo to GitHub
Go to render.com -> New -> Web Service
Connect your GitHub repo — Render auto-reads
render.yamlDeploy! Your MCP endpoint will be:
https://<your-app>.onrender.com/mcp
Connect your other project to the deployed server
# In your other project:
from mcp.client.streamable_http import streamablehttp_client
from mcp import ClientSession
import base64, asyncio
async def send_video(video_path: str, server_url: str):
with open(video_path, "rb") as f:
b64 = base64.b64encode(f.read()).decode()
async with streamablehttp_client(server_url) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
result = await session.call_tool(
"receive_video",
arguments={"video_base64": b64, "filename": "clip.mp4"}
)
print(result.content[0].text)
asyncio.run(send_video("myvideo.mp4", "https://your-app.onrender.com/mcp"))Available Tools
Tool | Args | Description |
|
| Receives a base64 video, saves to |
| — | Lists all saved videos |
|
| Deletes a video from the server |
Test with the included client
# stdio (local)
python send_video_client.py myvideo.mp4
# HTTP (local server running on port 8000)
python send_video_client.py myvideo.mp4 --url http://localhost:8000/mcp
# HTTP (deployed on Render)
python send_video_client.py myvideo.mp4 --url https://your-app.onrender.com/mcpLimitations
Issue | Notes |
Size overhead | Base64 adds ~33% to file size |
Large files | Videos >50 MB may strain memory / context windows |
Netlify | Cannot host persistent MCP HTTP servers — use Render instead |
Project structure
mcp/
├── video_mcp_server.py # MCP server (stdio + HTTP transport)
├── send_video_client.py # Test client (stdio + HTTP)
├── requirements.txt # Python dependencies
├── setup.ps1 # One-click setup script
├── render.yaml # Render deployment config
├── Procfile # Railway / Heroku deployment
├── .gitignore
└── received_videos/ # Videos saved here (auto-created)This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dpansumisra/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server