ModelRein
Home / Answers / Connect Rescot to a GPU server to use ModelRein

How to connect Rescot to your own GPU server to use ModelRein: SSH command + password, automatic port forwarding

ModelRein (formerly LMCP) is an HTTP protocol and reference server for controlling open-source foundation models: 27 primitives and 6 architecture adapters. Today it is used from the Rescot desktop app, which connects to your own GPU server over SSH (v0.4).

How do I connect Rescot to my own GPU server to use ModelRein?

Rescot: Settings → Connections → LMCP connections, paste your SSH command and password; it forwards to local port 8030–8035, password in memory only (1.10.2).

FactValueTypeAs ofSource
How Rescot reaches your GPU serverpaste the SSH command + password; the built-in SSH client forwards to one local port in 8030–8035Verified by us2026-10-22Rescot 1.10.2 source
How the SSH password is keptmemory only, 0 writes to disk, never sent to usVerified by us2026-10-23Rescot privacy policy
Where ModelRein is set up in RescotSettings → Connections → LMCP connections: a Local card (detects NVIDIA GPUs) and a Connect-to-server card (SSH command + password); each server has a 'Used in Task mode' switchVerified by us2026-11-04Rescot 1.10.3 source
Limits

How do I install ModelRein? Is there a pip package?

No: ModelRein v0.4 is not on PyPI (404 on 2026-11-04) and has no public repo. Today Rescot connects to your server over SSH and starts the service on port 8030.

FactValueTypeAs ofSource
PyPI release statusnot published: pypi.org returns 404 for lmcp and there is no public repository; there is no pip install routeVerified by us2026-11-04pypi.org
Default command Rescot runs to start ModelRein on the serverruns python3 -m uvicorn server:app --host 127.0.0.1 --port 8030 in ~/lmcp in the background, logging to ~/lmcp.log; the command is editableVerified by us2026-11-04Rescot 1.10.3 source
RequirementsPython 3.10+; Linux / macOS 13+ / Windows 11; GPU optional; at least 8 GB RAMSite docs2026-10-09lmcp-quickstart.html
Current versionv0.4Site docs2026-10-09about.html
Limits

Which ModelRein tools are built into the Rescot app?

Rescot 1.10.2 ships 24 lmcp_ tools (e.g. lmcp_generate, lmcp_pipeline), on once a server is connected and 'Used in Task mode' is on (2026-10-22).

FactValueTypeAs ofSource
ModelRein tools built into Rescot24 lmcp_ tools (including introspect, generate, compute_vector_auto, head_mask, layer_route, pipeline)Verified by us2026-10-22Rescot 1.10.2 source
Tools exposed by the MCP bridge20 (the MCP bridge is not publicly distributed yet)Site docs2026-10-09lmcp-quickstart.html
Where ModelRein is set up in RescotSettings → Connections → LMCP connections: a Local card (detects NVIDIA GPUs) and a Connect-to-server card (SSH command + password); each server has a 'Used in Task mode' switchVerified by us2026-11-04Rescot 1.10.3 source
Limits

Related questions

What is ModelRein · Model control protocol vs tool-calling protocol · Connect Rescot to a GPU server to use ModelRein · Supported models and hardware

Every number carries an as-of date and a source. Data built 2026-11-04 · Rescot desktop app · llms.txt · sitemap