← Discover MCPs and Agents
E
MCPAI & MLMCP Registry

EmpirioLabs AI

Every EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.

Links

README

From the repo.

EmpirioLabs AI

EmpirioLabs AI MCP server

Remote Model Context Protocol server for EmpirioLabs AI. Run 180+ AI models, image, video and speech generation, web search, batch jobs, GPU Cloud and hosted agents as tools with your EmpirioLabs account. It is a remote server, so there is nothing to install.

Server URLhttps://mcp.empiriolabs.ai/mcp (Streamable HTTP)
AuthenticationOAuth 2.1 (sign in with your EmpirioLabs account) or an EmpirioLabs API key as a bearer token
Registry nameai.empiriolabs/mcp in the official MCP Registry, version 1.2.0
Documentationhttps://docs.empiriolabs.ai/mcp
Supportsupport@empiriolabs.ai

Every model and feature EmpirioLabs adds is available here as it launches, at the same final prices and limits as the API. Connections use your prepaid credits, and you can disconnect any app under Settings in the dashboard.

Connect

Claude (web, desktop, mobile)

  1. Open Settings, then Connectors, and choose Add custom connector.
  2. Enter https://mcp.empiriolabs.ai/mcp as the URL. Leave the OAuth client fields empty.
  3. Click Connect, sign in to EmpirioLabs, review the request, and choose Allow access.

Claude Code:

claude mcp add --transport http empiriolabs https://mcp.empiriolabs.ai/mcp

Run /mcp inside Claude Code to complete the sign-in the first time. The repository is also a Claude Code plugin (.claude-plugin/plugin.json), so it can be installed from a plugin marketplace.

ChatGPT

  1. Open Settings, then Plugins, and turn on Developer mode.
  2. Choose Create app, enter https://mcp.empiriolabs.ai/mcp as the server URL with OAuth authentication, and create it.
  3. Finish the sign-in and choose Allow access. The server also provides the search and fetch tools ChatGPT uses for connectors, so it works in chat and in deep research.

Cursor, VS Code, Windsurf, Cline and other editors

Remote servers are configured with a URL. Sign in through OAuth when the editor prompts, or add an API key header:

{
  "mcpServers": {
    "empiriolabs": {
      "url": "https://mcp.empiriolabs.ai/mcp",
      "headers": {
        "Authorization": "Bearer sk-empiriolabs-your_key_here"
      }
    }
  }
}

VS Code reads the same shape from .vscode/mcp.json with a servers key and "type": "http". Codex CLI: codex mcp add empiriolabs --url https://mcp.empiriolabs.ai/mcp. Gemini CLI and Windsurf accept the JSON block above in their MCP settings. Cline: see llms-install.md.

Google Antigravity

Antigravity names the endpoint field serverUrl, not url. Put this in ~/.gemini/config/mcp_config.json, or in plugins/<name>/mcp_config.json to ship it with a plugin:

{
  "mcpServers": {
    "empiriolabs": {
      "serverUrl": "https://mcp.empiriolabs.ai/mcp",
      "headers": {
        "Authorization": "Bearer sk-empiriolabs-your_key_here"
      }
    }
  }
}

A server that fails to connect is silently absent from Antigravity's tool list rather than reported as an error, so check the key first if the tools do not appear.

Grok, Perplexity, Le Chat and Gemini

These assistants take the server as a custom connector; paste https://mcp.empiriolabs.ai/mcp and sign in when asked.

  • Grok: open grok.com/connectors, choose New Connector, then Custom, and enter the URL.
  • Perplexity: open Settings, then Connectors, choose Custom connector, then Remote, enter the URL with the Streamable HTTP transport and OAuth 2.0.
  • Le Chat: open Connectors, choose Add Connector, then the Custom MCP Connector tab, give it a name and enter the URL.
  • Gemini: open Settings & help, then Connected Apps, and add a custom app with the URL.

Any HTTP client

The server speaks JSON-RPC over POST https://mcp.empiriolabs.ai/mcp. Send Authorization: Bearer <API key or OAuth access token> and Accept: application/json, text/event-stream on every request.

curl "https://mcp.empiriolabs.ai/mcp" \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Accept: application/json, text/event-stream" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_models","arguments":{"modality":"image","limit":5}}}'

Tools

77 tools in 10 toolsets. The complete reference with every parameter is on the documentation page.

ToolsetWhat it covers
ModelsBrowse the model catalog, prices, capabilities, and parameters
TextRun chat, embeddings, reranking, and AI text detection (uses credits)
SearchRun web search, grounded answers, and research (uses credits)
MediaGenerate and edit images, video, audio, speech, transcription, and 3D (uses credits)
JobsCheck, wait for, and cancel generation jobs
AgentsRun and manage agent tasks (uses credits)
AccountRead usage history and the current balance
BatchUpload batch files and manage batch jobs (uses credits)
GPU CloudDeploy and manage GPU instances, clusters, and volumes (billable)
Hosted AgentsCreate and manage hosted agents (billable)

Profiles

Profiles expose a subset of toolsets at a shorter URL:

URLToolsets
https://mcp.empiriolabs.ai/mcpall
https://mcp.empiriolabs.ai/mcp/inferencemodels, text, search, jobs, account
https://mcp.empiriolabs.ai/mcp/mediamodels, media, jobs, account
https://mcp.empiriolabs.ai/mcp/cloudmodels, account, gpu, hosted_agents
https://mcp.empiriolabs.ai/mcp/no-mediamodels, text, search, jobs, agents, account, batch, gpu, hosted_agents

Combine toolsets with +, for example https://mcp.empiriolabs.ai/mcp/models+text+jobs.

Prompts

Ready-made requests that chain several tools; clients that support MCP prompts list them next to the tools.

PromptWhat it doesArguments
choose_modelCompare EmpirioLabs models for a task and recommend one, with a cheaper fallback and final prices.task, modality (optional), priority (optional)
research_with_citationsAnswer a question from live web research and cite every source.question, depth (optional)
generate_mediaCreate an image, video, audio track or 3D asset from a description and return the finished files.description, kind (optional), model (optional)
deploy_gpu_workloadRent a GPU on EmpirioLabs GPU Cloud, start a workload on it and report the endpoints and hourly cost.workload, gpu (optional), max_hourly_price (optional)
spend_reportSummarise the account balance, recent usage and everything that is still running and billing.period (optional)

Access and privacy

  • Read-only tools (catalog, jobs, usage) use no credits. Tools that run models, searches, agent tasks, batches or infrastructure use the prepaid credits of the connected account.
  • OAuth connections are listed under Settings > Connected applications in the dashboard, where Disconnect ends access right away.
  • Privacy policy and terms of service.

About this repository

This repository holds the public listing material for the hosted server: the registry server.json, the LobeHub and Claude plugin manifests, the icons, and the install notes. Every file that describes the tool surface is generated from the server's own definition, so it always matches what https://mcp.empiriolabs.ai/mcp serves. The server itself is operated by EmpirioLabs.ai LLC.

Config for your environment

Use the endpoint URL below in your config. No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "https://mcp.empiriolabs.ai/mcp"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.