MCP Server

The EmpirioLabs MCP server lets any Model Context Protocol client run the whole platform as tools: chat with every text model, generate images, video, audio, speech, 3D and transcripts, run web search and research, manage jobs, batches, GPU Cloud, and hosted agents, and read your usage and balance. It is a remote server, so there is nothing to install.

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 toolsets, and choose Allow access.

Claude Code uses the same server:

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

Run /mcp inside Claude Code to complete the sign-in the first time.

ChatGPT

1. Open Settings, then Connectors (or Apps), and enable Developer mode under Advanced.
2. Choose Create and enter https://mcp.empiriolabs.ai/mcp as the MCP server URL with OAuth authentication.
3. Finish the sign-in and approve the toolsets. The server also implements the search and fetch tools ChatGPT uses for connectors, so it works in chat and in deep research.

Cursor, VS Code, Windsurf, 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.

Any HTTP client

The server speaks JSON-RPC over POST https://mcp.empiriolabs.ai/mcp and answers with JSON. 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}}}'

How access works

• OAuth sign-in. Clients discover the authorization server from https://mcp.empiriolabs.ai/.well-known/oauth-protected-resource and register themselves automatically (dynamic client registration or a client ID metadata document). You approve the request on the EmpirioLabs dashboard. Approving creates a dedicated API key named after the application, and the client receives short-lived access tokens plus a refresh token for that key.
• API key. Send any active EmpirioLabs API key as the bearer token to get every tool without a sign-in step. This suits editors, scripts, and servers you control.
• Revoking. Pause or delete the connection’s key from API keys in the dashboard; the connection stops immediately and the client asks you to sign in again. Clients can also call the revocation endpoint listed in the authorization-server metadata.
• Scopes. Each toolset below is also an OAuth scope, so a client can request only what it needs and the consent screen shows exactly what was granted.

Profiles

Every toolset is available at https://mcp.empiriolabs.ai/mcp. Add a profile or a + separated list of toolsets to the path to expose a smaller, focused tool list, for example when a client works best with fewer tools or when you want a connection that cannot generate media.

Jobs and long-running generation

Image, video, audio, transcription, 3D, Compose, and agent tools return finished output URLs when the work completes within the wait window (default 40 seconds, at most 50). Otherwise they return a job_id and the client should call get_job, which can also wait, instead of starting the generation again. Output URLs are signed and expire, so download anything you want to keep. Chat, search, and research tools answer inline.

Example prompts

• “List the cheapest video models on EmpirioLabs, then generate a 5 second clip of waves at sunset with the best value one.”
• “Use EmpirioLabs to transcribe this recording, then summarize the action items with qwen3-7-max.”
• “Check my EmpirioLabs balance and show what I spent on image generation this week.”
• “Deploy an H100 on EmpirioLabs GPU Cloud with the vLLM template and tell me when it is ready.”
• “Run a web research task about the latest MCP specification changes and cite sources.”

Prices, limits, and errors

Tools run the same request path as the REST API, so the final prices on Models and Pricing, your account limits from Limits and API Keys, and the error messages from Errors and Status Codes all apply unchanged. A tool result with isError carries the same actionable message the API returns, for example when a model does not support the requested endpoint or when the account needs credits.

Privacy

Prompts and outputs pass through the request path without being stored for inspection; usage rows record only metadata such as model, tokens, cost, and status. See the Privacy Policy and Support.

Tool reference

Every tool is derived from the public OpenAPI document, so a newly documented endpoint becomes a tool automatically, and the reference below is regenerated from the server’s live manifest (https://mcp.empiriolabs.ai/manifest.json) on every docs build. search, fetch, and get_platform_status are built into the server; every other tool maps to one API operation.

Toolsets and scopes

Profiles

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

models tools

text tools

search tools

media tools

jobs tools

agents tools

account tools

batch tools

gpu tools

hosted_agents tools