Memvid MCP Server

1# memvid-mcp-server
2 
3 
4A Streamable-HTTP MCP Server that uses [memvid](https://github.com/Olow304/memvid) to encode text data into videos that can be quickly looked up with semantic search.
5 
6 
7Supported Actions:
8- `add_chunks`: Adds chunks to the memory video. Note: each time you add chunks, it resets the memory.mp4. Unsure if there is a way to incrementally add.
9- `search`: queries for the top-matching chunks. Returns 5 by default, but can be changed with top_k param.
10 
11## Running
12 
13Set up your environment:
14```bash
15python3.11 -m venv my_env
16. ./my_env/bin/activate
17pip install -r requirements.txt
18```
19 
20Run the server:
21```bash
22python server.py
23```
24 
25With a custom port:
26 
27```bash
28PORT=3002 python server.py
29```
30 
31## Connect a Client
32 
33You can connect a client to your MCP Server once it's running. Configure per the client's configuration. There is the [mcp-config.json](/mcp-config.json) that has an example configuration that looks like this:
34```json
35{
36  "mcpServers": {
37    "memvid": {
38      "type": "streamable-http",
39      "url": "http://localhost:3000"
40    }
41  }
42}
43```
44 
45### Acknowledgements
46 
47- Obviously the modelcontextprotocol and Anthropic teams for the MCP Specification. [https://modelcontextprotocol.io/introduction](https://modelcontextprotocol.io/introduction)
48- [HeyFerrante](https://heyferrante.com?ref=github-memvid-mcp-server) for enabling and sponsoring this project.
49