mcpSAFE
EmpirioLabs AI remote MCP server: 180+ AI models, media generation, web search, batch jobs, GPU Cloud and hosted agents as tools
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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.
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)
- Open Settings, then Connectors, and choose Add custom connector.
- Enter
https://mcp.empiriolabs.ai/mcpas the URL. Leave the OAuth client fields empty. - 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
- Open EmpirioLabs AI in the ChatGPT Plugins directory and install it.
- Sign in to EmpirioLabs, review the request, and choose Allow access.
- Mention @EmpirioLabs AI in a chat to
f1f6f3872f49OBSERVED · 2026-10-11Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
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.
2. **API key**: create a key at https://platform.empiriolabs.ai (API keys page) and send it as a bearer token.
Gates applied: no_behavioural_pass.
f1f6f3872f49full audit observations/trust-audit/mcp-server/empiriolabs-ai__mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | f1f6f3872f49 | SAFE | B | 89 | first audit |
Questions
What is the mcp MCP server?
EmpirioLabs AI remote MCP server: 180+ AI models, media generation, web search, batch jobs, GPU Cloud and hosted agents as tools
Is mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does mcp need?
It reads LOBEHUB_CREDENTIALS_SEED from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mcp run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (f1f6f3872f49), read on 2026-10-11. The repository is watched and re-audited when it changes.