// SCAN REPORT

Universal AI Hub

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 30/06/2026

How to control Universal AI Hub ↓

TOOL MAP

What Universal AI Hub exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Universal AI Hub tools

Execute · High llm_complete Based on the server context (a multi-LLM gateway) and the tool name 'llm_complete', this tool almost certainly sends prompts to an external LLM provider and returns completions — an external operation whose effects depen

1 of Universal AI Hub's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Universal AI Hub

PolicyLayer is an MCP gateway — it sits between your AI agents and Universal AI Hub, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "get_model_info": {
    "limits": [
      {
        "counter": "get_model_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Universal AI Hub — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON UNIVERSAL AI HUB →

Instant setup, no code required.

FULL CATALOGUE

All 5 Universal AI Hub tools

EXECUTE 1 tools

Execute llm_complete llm_complete

READ 4 tools

Read get_model_info get_model_info Read health_check Health check endpoint for HuggingFace Spaces and monitoring systems. Read list_active_tools List all active providers and registered tools. Read web_search web_search

FAQ

Questions about Universal AI Hub

Is the Universal AI Hub MCP server safe to use without restrictions? +

The Universal AI Hub server is primarily read-only with 4 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Universal AI Hub MCP server expose? +

5 tools across 2 categories: Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Universal AI Hub? +

Register the Universal AI Hub MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Universal AI Hub tool call.

Deterministic rules across all 5 Universal AI Hub tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UNIVERSAL AI HUB →

Instant setup, no code required.

5 Universal AI Hub tools catalogued and risk-classified — across an index of 43,000+ MCP servers.