Search / io.github.setheerwagen/mcp-modelmanager
Model Manager
L0· runs locallyManage your local model machine over MCP: state, model pull/remove, service switch, LoRA training
v1.0.3 · active · repository · descriptor JSON · versions
Search / io.github.setheerwagen/mcp-modelmanager
L0· runs locallyManage your local model machine over MCP: state, model pull/remove, service switch, LoRA training
v1.0.3 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"mcp-modelmanager": {
"command": "uvx",
"args": [
"mcp-modelmanager==1.0.3"
],
"env": {
"MM_VM_HOST": "${MM_VM_HOST}",
"MM_VM_USER": "${MM_VM_USER}",
"MM_CONTAINER_ROOT": "${MM_CONTAINER_ROOT}",
"MM_MAX_TIER": "read"
}
}
}
}claude mcp add mcp-modelmanager -e "MM_VM_HOST=${MM_VM_HOST}" -e "MM_VM_USER=${MM_VM_USER}" -e "MM_CONTAINER_ROOT=${MM_CONTAINER_ROOT}" -e "MM_MAX_TIER=read" -- uvx mcp-modelmanager==1.0.3[mcp_servers.mcp-modelmanager]
command = "uvx"
args = ["mcp-modelmanager==1.0.3"]
env = { "MM_VM_HOST" = "${MM_VM_HOST}", "MM_VM_USER" = "${MM_VM_USER}", "MM_CONTAINER_ROOT" = "${MM_CONTAINER_ROOT}", "MM_MAX_TIER" = "read" }
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mcp-modelmanager": {
"type": "local",
"command": [
"uvx",
"mcp-modelmanager==1.0.3"
],
"enabled": true,
"environment": {
"MM_VM_HOST": "{env:MM_VM_HOST}",
"MM_VM_USER": "{env:MM_VM_USER}",
"MM_CONTAINER_ROOT": "{env:MM_CONTAINER_ROOT}",
"MM_MAX_TIER": "read"
}
}
}
}{
"mcpServers": {
"mcp-modelmanager": {
"command": "uvx",
"args": [
"mcp-modelmanager==1.0.3"
],
"env": {
"MM_VM_HOST": "${MM_VM_HOST}",
"MM_VM_USER": "${MM_VM_USER}",
"MM_CONTAINER_ROOT": "${MM_CONTAINER_ROOT}",
"MM_MAX_TIER": "read"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-modelmanager&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJtY3AtbW9kZWxtYW5hZ2VyPT0xLjAuMyJdLCJlbnYiOnsiTU1fVk1fSE9TVCI6IiR7TU1fVk1fSE9TVH0iLCJNTV9WTV9VU0VSIjoiJHtNTV9WTV9VU0VSfSIsIk1NX0NPTlRBSU5FUl9ST09UIjoiJHtNTV9DT05UQUlORVJfUk9PVH0iLCJNTV9NQVhfVElFUiI6InJlYWQifX0%3D"
}{
"servers": {
"mcp-modelmanager": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-modelmanager==1.0.3"
],
"env": {
"MM_VM_HOST": "${MM_VM_HOST}",
"MM_VM_USER": "${MM_VM_USER}",
"MM_CONTAINER_ROOT": "${MM_CONTAINER_ROOT}",
"MM_MAX_TIER": "read"
}
}
}
}{
"mcpServers": {
"mcp-modelmanager": {
"command": "uvx",
"args": [
"mcp-modelmanager==1.0.3"
],
"env": {
"MM_VM_HOST": "${MM_VM_HOST}",
"MM_VM_USER": "${MM_VM_USER}",
"MM_CONTAINER_ROOT": "${MM_CONTAINER_ROOT}",
"MM_MAX_TIER": "read"
}
}
}
}extensions:
"mcp-modelmanager":
enabled: true
name: "mcp-modelmanager"
type: stdio
cmd: "uvx"
args:
- "mcp-modelmanager==1.0.3"
envs:
"MM_VM_HOST": "${MM_VM_HOST}"
"MM_VM_USER": "${MM_VM_USER}"
"MM_CONTAINER_ROOT": "${MM_CONTAINER_ROOT}"
"MM_MAX_TIER": "read"
timeout: 300
This is a local package: the command runs on your machine.
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)stability.changes, stability.rug_pulltool list unknownNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo ~liveness-unmeasured +updated-7d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] PyPIthis version is not known to the dependency resolver
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
mcp-modelmanager | pypi | 1.0.3 | – |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
1 other active names share this repository: io.github.setheerwagen/mcp-ollama-vllm
{
"name": "io.github.setheerwagen/mcp-modelmanager",
"title": "Model Manager",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.0.3",
"packages": [
{
"version": "1.0.3",
"transport": {
"type": "stdio"
},
"identifier": "mcp-modelmanager",
"registryType": "pypi",
"environmentVariables": [
{
"name": "MM_VM_HOST",
"format": "string",
"isRequired": true,
"description": "Address of the model machine (127.0.0.1, LAN IP or tunnel/VPN address)"
},
{
"name": "MM_VM_USER",
"format": "string",
"isRequired": true,
"description": "SSH user on the model machine"
},
{
"name": "MM_CONTAINER_ROOT",
"format": "filepath",
"isRequired": true,
"description": "Root directory on the machine holding all model, adapter and cache data"
},
{
"name": "MM_MAX_TIER",
"format": "string",
"default": "read",
"description": "Highest tool tier exposed: read, control or destructive"
},
{
"name": "MM_ENABLED_OPERATIONS",
"format": "string",
"description": "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"
},
{
"name": "MM_VM2_HOST",
"format": "string",
"description": "Optional: address of a second machine sharing the GPU, used to interpret unreachability. Leave empty if there is only one machine"
}
]
}
],
"repository": {
"url": "https://github.com/setheerwagen/local-ai-mcp-servers",
"source": "github",
"subfolder": "mcp-modelmanager"
},
"description": "Manage your local model machine over MCP: state, model pull/remove, service switch, LoRA training"
}