Agent Update

Connect

LiteLLM Proxy → Agent Update

A self-hosted proxy that puts one OpenAI-compatible API in front of many providers. It can also aggregate MCP servers into one gateway.

LiteLLM Proxy talks to Agent Update over MCP. The server is https://api.tryagentupdate.com/v1/mcp, the transport is Streamable HTTP, and the credential is one header.

Where it goes: proxy config.yaml

Setup

proxy config.yaml
mcp_servers:
  agent_update:
    url: "https://api.tryagentupdate.com/v1/mcp"
    transport: "http"
    auth_type: "bearer_token"
    auth_value: "os.environ/AGENT_UPDATE_TOKEN"
Static-header alternative
static_headers: { Authorization: "Bearer au_live_..." }

Before you file a bug

transport defaults to sse, so set it explicitly, and the value is exactly "http" — not streamable-http. auth_value takes the RAW token: LiteLLM builds Bearer <auth_value> itself, so prefixing it yourself gives you Bearer Bearer and a 401. Use the os.environ/VAR indirection on auth_value rather than pasting the PAT into the file. If you use static_headers instead, note they were not forwarded during session.initialize() and tool discovery on v1.80.15 (issue #19341, fixed by #19366), so stay current. This surface is useful when you want one MCP endpoint fronting many downstream agents.

Check it worked

Ask the agent to text you. A 401 means the token is wrong, or the word Bearer is in there twice. No tool at all means the transport string is wrong. Both are covered in troubleshooting.

Next

The five tools and their arguments are on the MCP page. The same tools over plain HTTP are on the REST page. Every other tool is on the docs index.

← All docs