Connect via MCP
The fastest path is the hosted HTTP endpoint — no install, just a token.
Umtri runs a hosted Model Context Protocol server at https://mcp.umtri.io. Point any MCP client at it and authenticate with your umtri_pat_… token as a Bearer header — nothing to clone or install. Generate a token first (see Generate an API token).
Claude Code
claude mcp add --transport http umtri https://mcp.umtri.io \
--header "Authorization: Bearer umtri_pat_xxxxxxxxxxxxxxxx"
Add --scope user for all projects (global) or --scope local for the current one. Verify with claude mcp list — you should see umtri: ✓ Connected; inside a session, /mcp lists the tools.
Gemini CLI
gemini mcp add --transport http \
--header "Authorization: Bearer umtri_pat_xxxxxxxxxxxxxxxx" \
umtri https://mcp.umtri.io
Scope with --scope user (global) or --scope project.
Codex
Codex references the token through an environment variable. Set it, then add the server to ~/.codex/config.toml (global) or .codex/config.toml (project):
export UMTRI_API_TOKEN="umtri_pat_xxxxxxxxxxxxxxxx"
# ~/.codex/config.toml
[mcp_servers.umtri]
url = "https://mcp.umtri.io"
bearer_token_env_var = "UMTRI_API_TOKEN"
Any MCP client (JSON)
Clients that take a config object use the same shape:
{
"mcpServers": {
"umtri": {
"type": "http",
"url": "https://mcp.umtri.io",
"headers": { "Authorization": "Bearer umtri_pat_xxxxxxxxxxxxxxxx" }
}
}
}
Run it locally (stdio)
Prefer to run the server yourself — e.g. to pin a version or point at a self-hosted API? The umtri-mcp package speaks stdio and takes UMTRI_API_TOKEN as an environment variable.
claude mcp add umtri \
-e UMTRI_API_TOKEN=umtri_pat_xxxxxxxxxxxxxxxx \
--transport stdio \
-- npx -y umtri-mcp
Source: github.com/bepuljang/umtri-mcp — Apache-2.0.
Other variables
UMTRI_API_BASE— defaults tohttps://api.umtri.io. Override only if self-hosting the API.
The token saves without validation, so a bad token connects but every call fails. If tools do not appear, re-check the token and its scope.