
ModelsLab Agent Control Plane
io.github.ModelsLabv1.0.0Updated Oct 2, 2026
Account, billing, team, API key and model discovery tools for agents that use ModelsLab.
Overview
AI-generated overview
Lets an assistant manage ModelsLab account, billing, team, API keys, and model discovery through a remote control plane.
- What it does
- This remote MCP server exposes ModelsLab's agent control plane, covering account, billing, team, API key, and model discovery operations. An assistant can look up available models and manage the credentials and account settings tied to a ModelsLab subscription. It connects over streamable HTTP to the ModelsLab endpoint rather than running locally.
- When to use it
- Use it when an assistant needs to work with ModelsLab account administration, billing details, team membership, API key handling, or model listings as part of a workflow. It is not needed if you only call ModelsLab generation APIs directly.
- Requirements
- A remote streamable HTTP connection to the ModelsLab endpoint. Authentication uses an Authorization header carrying a ModelsLab personal access token (Sanctum); the token is required. No local runtime or packages are declared.
Before you install
The Authorization header carries a ModelsLab personal access token, so treat it as a secret and avoid exposing it in logs or shared transcripts. Billing and API key tools may change account settings or incur charges, and team tools can affect other members' access. Confirm what each action does before letting an assistant run it.
Installation
In SourceWeft
- Open ModelsLab Agent Control Plane in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"modelslab-agents": {
"type": "http",
"url": "https://modelslab.com/mcp/agents"
}
}
}README
This repository has no README.
Tools
0Tool metadata has not been indexed yet.
Version history
1- v1.0.0LatestOct 2, 2026
