Back to code-only MCP servers

promptchain

updated this year

Load, unload, and swap any number of local LLMs (LM Studio, Ollama, llama.cpp, ...) with full client-side control — plus unified streaming for local and cloud backends and an MCP server so agents can manage your VRAM.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/atharva557/prompt-chaining
Package
pypi: promptchain
Run (stdio)
uvx promptchain
The usual command for this package registry; check the repository README for required settings.
License
MIT
Last update
2026-07-18
Homepage
github.com/atharva557/Prompt-Chaining

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.