← Index

Model Manager

io.github.setheerwagen/mcp-modelmanagerv1.0.1Other

Manage your local model machine over MCP: state, model pull/remove, service switch, LoRA training

The current version, v1.0.1, was published to the official MCP registry on 2026-09-01. It is distributed as mcp-modelmanager on PyPI, filed under Other by this index, and declares 6 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using Model Manager in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Auditable install path →Watch it hold a drift →
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-09-02).

Contracts can change after screening, with no version bump. The gate pins Model Manager’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Environment variables
MM_VM_HOST
required

Address of the model machine (127.0.0.1, LAN IP or tunnel/VPN address)

MM_VM_USER
required

SSH user on the model machine

MM_CONTAINER_ROOT
required

Root directory on the machine holding all model, adapter and cache data

MM_MAX_TIER

Highest tool tier exposed: read, control or destructive

MM_ENABLED_OPERATIONS

Optional comma-separated allowlist of exact tool names, applied on top of MM_MAX_TIER; a typo aborts startup. Empty means everything within MM_MAX_TIER

MM_VM2_HOST

Optional: address of a second machine sharing the GPU, used to interpret unreachability. Leave empty if there is only one machine

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
15
installability
25
documentation
15
stability
10
Alternatives in Other
AgentRoam
ai.agentroam/agentroam

Buy travel eSIMs, gift cards and mobile top-ups with crypto — user confirms before any order.

Authoryze
ai.authoryze/authoryze

Give your AI agent a spending limit: approval controls and single-use virtual cards.

Ollama / vLLM Bridge
io.github.setheerwagen/mcp-ollama-vllm

Call your local Ollama or vLLM model over MCP with schema-validated JSON output