Skip to main content
Because Ultra is itself an MCP server, it exposes built-in tools that your AI client can call directly. This means you can search for, add, migrate, and monitor MCP servers without leaving your conversation.
These tools are available automatically when Ultra is connected to your AI client. No extra configuration needed.

Available Tools

Ultra provides four built-in tools:
ToolWhat it does
ultra_statusCheck Ultra’s version, connected servers, and total tool count
ultra_searchSearch the official MCP registry and npm for servers
ultra_addInstall a server from a registry or URL, hot-loaded immediately
ultra_migrateDiscover and import MCP servers already configured in your clients
In addition to these management tools, Ultra aggregates all tools from your upstream servers and exposes them through a single connection. Each upstream tool is namespaced with its server name (e.g., github:search_code, notion:search).

ultra_status

Check that Ultra is running and see what’s connected. Example prompts:
  • “Check my Ultra status”
  • “How many MCP tools do I have connected?”
Returns: Ultra version, number of upstream servers, and total aggregated tool count. Search the official MCP registry and npm for servers to add. Example prompts:
  • “Search for a Notion MCP server”
  • “Find MCP servers for databases”
  • “Search npm for filesystem MCP servers”
Parameters:
ParameterRequiredDescription
queryYesSearch term (e.g., “filesystem”, “github”, “database”)
limitNoMax results to return (default: 10)
sourceNoFilter by official or npm
Returns: Server names, descriptions, versions, authors, download counts, and required environment variables.

ultra_add

Add an MCP server and make its tools available immediately. No restart required. Example prompts:
  • “Add the GitHub MCP server”
  • “Install the filesystem server so you can read my project files”
  • “Add the Slack MCP server at https://mcp.slack.com/mcp
Parameters:
ParameterRequiredDescription
serverYesPackage name (e.g., @modelcontextprotocol/server-filesystem) or URL
nameNoCustom name for the server
envNoEnvironment variables (e.g., {"GITHUB_TOKEN": "ghp_..."})
disabledNoAdd in disabled state (default: false)
What happens:
  1. Ultra resolves the server from the registry or connects to the URL
  2. Validates any required environment variables
  3. Adds the server to your Ultra config
  4. Hot-loads the server immediately so new tools are available without restarting
After adding a server, restart your MCP client so it picks up the new tools from Ultra.

ultra_migrate

Discover MCP servers already configured in your AI clients and import them into Ultra. Example prompts:
  • “Migrate my existing MCP servers to Ultra”
  • “What MCP servers do I have that aren’t going through Ultra yet?”
Parameters:
ParameterRequiredDescription
actionYesdiscover to list available servers, execute to migrate them
serversNoSpecific server names to migrate (execute only)
What happens:
  1. Ultra scans your AI clients (Claude Desktop, Cursor, Codex, etc.) for configured MCP servers
  2. Shows you what it found, including command and connection details
  3. On execute, imports selected servers into Ultra’s config and hot-reloads them
  4. Duplicate servers configured across multiple clients are merged automatically
After migration, restart your MCP client(s) so they route through Ultra instead of connecting directly.

Upstream Tool Aggregation

Beyond its built-in tools, Ultra aggregates every tool, resource, and prompt from all your connected upstream servers into a single MCP connection. Your AI client sees one server (Ultra) with all tools available. Tools are automatically namespaced by server name to avoid conflicts:
github:search_code
github:create_pull_request
notion:search
notion:create_page
filesystem:read_file
filesystem:write_file
This means you can add a new upstream server and its tools appear alongside everything else. No client reconfiguration needed.

Upstream Servers

Add and configure MCP servers manually via CLI or config file

Migrate Servers

Import existing servers using the CLI wizard