Agent Update

Connect

LibreChat → Agent Update

An open-source, self-hosted ChatGPT-style web UI that fronts many model providers at once.

LibreChat 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: librechat.yaml

Setup

librechat.yaml
mcpServers:
  agent-update:
    type: streamable-http
    url: https://api.tryagentupdate.com/v1/mcp
    headers:
      Authorization: 'Bearer ${AGENT_UPDATE_TOKEN}'
    timeout: 30000
.env
AGENT_UPDATE_TOKEN=au_live_...

Before you file a bug

The transport string is hyphenated streamable-http, and the top-level key is camelCase mcpServers — unlike VS Code, which wants servers. ${ENV_VAR} interpolation inside headers is confirmed to work here, so the config above is safe to publish as-is with the token in .env. timeout is milliseconds and defaults to 30000. Servers initialise at application startup, so a config change needs a restart, not a page reload. For a multi-tenant deployment, {{LIBRECHAT_USER_ID}}-style placeholders are the route to per-user PATs.

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