Aggregator MCP Server

LiteLLM Multi Model API

Name: LiteLLM Multi Model API
Author: BerriAI

Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.

Scan found nothing by BerriAI3MITPythonIntermediatestdio

Install

Claude Code

claude mcp add berriai-litellm-agent-mcp -- uvx litellm-mcp

Cursor

{
  "mcpServers": {
    "berriai-litellm-agent-mcp": {
      "command": "uvx",
      "args": [
        "litellm-mcp"
      ]
    }
  }
}

VS Code

{
  "mcp": {
    "servers": {
      "berriai-litellm-agent-mcp": {
        "command": "uvx",
        "args": [
          "litellm-mcp"
        ]
      }
    }
  }
}

Windsurf

{
  "mcpServers": {
    "berriai-litellm-agent-mcp": {
      "command": "uvx",
      "args": [
        "litellm-mcp"
      ]
    }
  }
}

Claude Desktop

{
  "mcpServers": {
    "berriai-litellm-agent-mcp": {
      "command": "uvx",
      "args": [
        "litellm-mcp"
      ]
    }
  }
}

Safety Report

67% Scan found nothing

Scanned 5 months ago

4 passed 2 warnings

Security

Authentication

details

Weak auth signals: env_required

Warning

CORS Policy

details

stdio transport — CORS not applicable

N/A

Rate Limiting

details

No rate limiting mechanism detected

Info

Known CVEs

details

No known CVEs in dependencies

Pass

Code Quality

Dependency Audit

details

No known vulnerable dependencies detected

Pass

Dangerous Patterns

details

No dangerous code patterns detected

Pass

License

details

License: MIT

Pass

Community

Maintenance Status

details

Last commit 6 months ago

Warning

Learn about our security methodology →

Compatibility

Claude CodeFull support

Tested

CursorFull support

Tested

VS CodeFull support via Copilot

Tested

WindsurfFull support

Tested

Claude DesktopFull support

Tested

Frequently Asked Questions

What is LiteLLM Multi Model API?

Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.

Is LiteLLM Multi Model API safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone LiteLLM Multi Model API and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. None of them matched. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to LiteLLM Multi Model API?

Similar MCP servers include Metatool App, PaperBanana, MCPJungle. Each serves a similar purpose but may differ in features, language, and compatibility.