ModelsLab MCP server
Commit Nov 1, 2026Access over 10,000 AI models to generate images, video, audio, and text through a single MCP interface.
Also known as ModelsLab/modelslab-mcp, modelslab-agents
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 1, 2026
- License
- MIT
What is ModelsLab MCP?
ModelsLab accesses over 10,000 AI models to generate images, video, audio, and text through a single MCP interface.
Summary generated from the project's README
About ModelsLab MCP server
ModelsLab Agent Control Plane provides a remote MCP server that connects developers to a massive library of over 10,000 AI models. This hosted service allows users to generate images, video, audio, and text through a single interface without local installation. It supports various media tasks including text-to-image, lip-sync, music-generation, and chat-completion. Users can access specific models like Flux, Kling, or ElevenLabs-class voices by first using the discovery tools.
Integration is handled via streamable HTTP, making it compatible with clients like Claude Desktop, Cursor, Windsurf, and VS Code. Authentication is managed through either OAuth 2.1 or a Bearer API key. Because most generation tasks are asynchronous, the server uses a job system where users call fetch-generation with a specific ID to monitor the status of their requests until they reach a success or error state.
What you can do with it
- 1Generate diverse multimedia contentCreate images, videos, and music tracks using a single command through the MCP interface.
- 2Discover available AI modelsFind specific model IDs for different providers to ensure high quality outputs.
- 3Monitor asynchronous generation jobsTrack the progress of long-running media generation tasks using unique identifiers.
Written from the project's README. Every use case is checked against a quote from it.
How to install ModelsLab MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ModelsLab MCP in Claude Code
$ claude mcp add --transport http modelslab-agents https://modelslab.com/mcp/agentsInstall ModelsLab MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"modelslab-agents": {
"url": "https://modelslab.com/mcp/agents"
}
}
}Install ModelsLab MCP in VS Code
.vscode/mcp.json
{
"servers": {
"modelslab-agents": {
"type": "http",
"url": "https://modelslab.com/mcp/agents"
}
}
}Install ModelsLab MCP in VS Code CLI
$ code --add-mcp '{"name":"modelslab-agents","type":"http","url":"https://modelslab.com/mcp/agents"}'Install ModelsLab MCP in Codex
$ codex mcp add modelslab-agents --url https://modelslab.com/mcp/agentsInstall ModelsLab MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.modelslab-agents] url = "https://modelslab.com/mcp/agents"
Install ModelsLab MCP in Gemini CLI
$ gemini mcp add -s user --transport http modelslab-agents https://modelslab.com/mcp/agentsInstall ModelsLab MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"modelslab-agents": {
"url": "https://modelslab.com/mcp/agents",
"type": "http"
}
}
}Configuration
MODELSLAB_API_KEY
| Name | Description | |
|---|---|---|
| MODELSLAB_API_KEY | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemodelslab/modelslab-mcp is public and reachablegithub.com/modelslab/modelslab-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-01github.com/modelslab/modelslab-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 143 msPass
README
View on GitHubModelsLab runs a hosted, remote MCP server. There is nothing to install: point your MCP client at the URL below and sign in with OAuth, or send your ModelsLab API key.
| Server URL | https://modelslab.com/mcp/v7 |
| Transport | Streamable HTTP |
| Auth | OAuth 2.1 (PKCE + dynamic client registration), or Authorization: Bearer <API key> |
| API key | modelslab.com/dashboard/api-keys |
| Server card | /.well-known/mcp/server-card.json |
| Official registry | io.github.ModelsLab/modelslab |
Tools
| Category | Tools |
|---|---|
| Discovery | list-models, list-providers |
| Image | text-to-image, image-to-image, inpaint-image, fetch-image |
| Video | text-to-video, image-to-video, video-to-video, lip-sync, motion-control, fetch-video |
| Audio | text-to-speech, speech-to-text, speech-to-speech, sound-generation, music-generation, song-extender, song-inpaint, dubbing, fetch-audio |
| LLM | chat-completion |
| Jobs | fetch-generation |
Most generation is asynchronous. A tool returns "status": "processing" with an id; call fetch-generation with that id until the status is success or error. Use list-models first to get a valid model_id (Flux, Qwen Image, Seedream, Kling, Veo, Wan, Hailuo, ElevenLabs-class voices, open-source LLMs, and more).
Setup
Claude (claude.ai and Claude Desktop)
Settings → Connectors → Add custom connector → URL https://modelslab.com/mcp/v7. Claude detects OAuth and opens the ModelsLab sign-in page.
Claude Code
claude mcp add --transport http modelslab https://modelslab.com/mcp/v7
Or with an API key:
claude mcp add --transport http modelslab https://modelslab.com/mcp/v7 \
--header "Authorization: Bearer $MODELSLAB_API_KEY"
Cursor
~/.cursor/mcp.json:
{
"mcpServers": {
"modelslab": {
"url": "https://modelslab.com/mcp/v7",
"headers": { "Authorization": "Bearer YOUR_MODELSLAB_API_KEY" }
}
}
}
VS Code (GitHub Copilot)
.vscode/mcp.json:
{
"servers": {
"modelslab": {
"type": "http",
"url": "https://modelslab.com/mcp/v7",
"headers": { "Authorization": "Bearer ${input:modelslab-key}" }
}
},
"inputs": [
{ "type": "promptString", "id": "modelslab-key", "description": "ModelsLab API key", "password": true }
]
}
Windsurf
~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"modelslab": {
"serverUrl": "https://modelslab.com/mcp/v7",
"headers": { "Authorization": "Bearer YOUR_MODELSLAB_API_KEY" }
}
}
}
Gemini CLI
~/.gemini/settings.json:
{
"mcpServers": {
"modelslab": {
"httpUrl": "https://modelslab.com/mcp/v7",
"headers": { "Authorization": "Bearer YOUR_MODELSLAB_API_KEY" }
}
}
}
OpenAI Codex CLI
~/.codex/config.toml:
[mcp_servers.modelslab]
url = "https://modelslab.com/mcp/v7"
bearer_token_env_var = "MODELSLAB_API_KEY"
Clients that only speak stdio
Use mcp-remote:
{
"mcpServers": {
"modelslab": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://modelslab.com/mcp/v7",
"--header", "Authorization: Bearer ${MODELSLAB_API_KEY}"],
"env": { "MODELSLAB_API_KEY": "YOUR_MODELSLAB_API_KEY" }
}
}
}
Example prompts
- "List the ModelsLab video models, then make a 5 second clip of a paper boat in the rain with the best one."
- "Generate a product photo of a ceramic mug on a wooden table, 1024x1024."
- "Turn this paragraph into speech with a calm British voice."
- "Write a 30 second lo-fi track with soft piano."
Other servers
| URL | What it does | Auth |
|---|---|---|
https://modelslab.com/mcp/v8 |
Next-generation v8 generation APIs | OAuth or API key |
https://modelslab.com/mcp/agents |
Account, billing, team, API key and model discovery for autonomous agents | Agent token |
Pricing
MCP calls bill the same as the REST API. Plans start at $21/month; the $149/month plan gives unlimited generations on open-source models. See modelslab.com/pricing.
About ModelsLab
ModelsLab is an AI API platform with 10,000+ models, 400,000+ registered users and 500 million+ API requests served, running on its own GPU datacenter. Founded in 2022.
License
The documentation and config files in this repository are MIT licensed. The hosted service is covered by the ModelsLab terms.
ModelsLab MCP questions
How do I add ModelsLab MCP to Claude Code?
Run claude mcp add --transport http modelslab-agents https://modelslab.com/mcp/agents in your terminal. Add --scope user to make it available in every project.
How do I add ModelsLab MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How does the generation process work for asynchronous tools?
Most generation tools return a processing status and an ID; you must then use the fetch-generation tool with that ID to check for success or error.
What is the pricing for using MCP calls?
MCP calls are billed the same as the REST API, with plans starting at $21 per month.