skills.rest
BerriAI
BerriAIOFFICIAL
Explore all skills by this author →
WebsiteGitHub

add-agent

Create an AI agent on a LiteLLM proxy via POST /v1/agents.

77|12|Updated Mar 14, 2026
Search Tags:#ai#agent#curl#proxy#admin#liteellm
One-click install
npx skills add https://github.com/BerriAI/litellm-skills --skill add-agent-berriai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-agent
Source: https://github.com/BerriAI/litellm-skills/tree/main/add-agent
Command: npx skills add https://github.com/BerriAI/litellm-skills --skill add-agent-berriai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creates an AI agent on a live LiteLLM proxy, handling the agent name, the underlying model, and optional MCP server access, then calls POST /v1/agents.

Core Features & Use Cases

  • Provision new agents by specifying a unique name and the model to run, with optional MCP server access for enhanced tool integrations.
  • Manage agents via REST endpoints: create (POST /v1/agents), view, list, and delete agents, enabling centralized control across teams.

Quick Start

Provide the agent name, choose a model, optionally specify MCP servers, and execute the curl command to create the agent.

Frequently Asked Questions about add-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an AI agent on a LiteLLM proxy?▼

To create an AI agent on a LiteLLM proxy, you POST to the /v1/agents endpoint with proper authentication, providing the agent name, model, description, and optional MCP servers for tool integration.

What information do I need to configure a new agent via the LiteLLM REST API?▼

Configuring a new agent via the LiteLLM REST API requires a unique agent name, the underlying model to run, and a description. You can also optionally specify MCP servers to enable enhanced tool integrations.

Can I attach MCP servers to an AI agent when using a LiteLLM proxy?▼

Yes, you can attach MCP servers when creating an AI agent on a LiteLLM proxy. Specifying MCP servers during the POST /v1/agents request enables optional MCP access for enhanced tool integrations.

Does managing agents on a LiteLLM proxy support listing and deleting via REST endpoints?▼

Managing agents on a LiteLLM proxy supports centralized control via REST endpoints. Admins can create, view, list, and delete agents across teams using the available API endpoints with proper authentication.

Do I need admin authentication to POST agents to a live LiteLLM proxy?▼

Yes, admin authentication is required to POST agents to a live LiteLLM proxy. The process applies to scenarios where admins need to configure models and manage agents securely via the REST endpoints.

Related Skills

Explore More Software Engineering Skills→
BerriAIBerriAI
77

update-user

Update existing LiteLLM proxy users via the POST /user/update endpoint.

Official
Intermediate
BerriAIBerriAI
77

delete-team

Deletes specified teams from a LiteLLM proxy via authenticated JSON request.

Official
Intermediate
BerriAIBerriAI
77

add-mcp

Register MCP servers on a live LiteLLM proxy via POST /v1/mcp/server.

Official
Intermediate
xixu-mexixu-me
71

running-claude-code-via-litellm-copilot

Route Claude Code requests through a local LiteLLM proxy to GitHub Copilot.

Community
Advanced