Skip to content

Connecting MCP clients

unifi-mcp supports both standard MCP transports:

Transport How it runs Best for
Streamable HTTP (the default in the image) One long-running container. Clients connect to http://<host>:8080/mcp. Most setups. One server can be shared by several clients and machines.
stdio The client starts a fresh container for each session with docker run -i. A single machine, no network service, or clients that only support stdio.

The HTTP endpoint is stateless: each request is handled on its own, so you can restart the container at any time. When MCP_AUTH_TOKEN is set, every request must send Authorization: Bearer <token>.

In the examples below, replace <docker-host> with the machine running the container and <token> with your MCP_AUTH_TOKEN.

Terminal window
claude mcp add --transport http unifi http://<docker-host>:8080/mcp \
--header "Authorization: Bearer <token>"

Add --scope user to make it available in every project, or --scope project to save it in a .mcp.json you can share with your team. Don’t commit the token: in .mcp.json, reference an environment variable instead:

{
"mcpServers": {
"unifi": {
"type": "http",
"url": "http://<docker-host>:8080/mcp",
"headers": { "Authorization": "Bearer ${UNIFI_MCP_TOKEN}" }
}
}
}

Run claude mcp list to check the connection, and /mcp inside Claude Code to see the tools. The built-in prompts are available as slash commands, such as /mcp__unifi__security_review.

Claude Desktop starts local MCP servers over stdio, so use stdio mode. Open Settings → Developer → Edit Config and add:

{
"mcpServers": {
"unifi": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "MCP_TRANSPORT=stdio",
"-e", "UNIFI_URL", "-e", "UNIFI_API_KEY",
"ghcr.io/mattoddie/unifi-mcp:latest"
],
"env": {
"UNIFI_URL": "https://192.168.1.1",
"UNIFI_API_KEY": "your-api-key"
}
}
}
}

Restart Claude Desktop. The tools appear under the tools (🔨) menu, and the prompts appear under + → Add from unifi.

Create .vscode/mcp.json in your workspace, or run MCP: Add Server from the command palette:

{
"inputs": [
{ "id": "unifi-token", "type": "promptString", "description": "unifi-mcp token", "password": true }
],
"servers": {
"unifi": {
"type": "http",
"url": "http://<docker-host>:8080/mcp",
"headers": { "Authorization": "Bearer ${input:unifi-token}" }
}
}
}

VS Code asks for the token once and stores it securely. Use the tools from Copilot Chat in Agent mode.

Add to ~/.cursor/mcp.json for all projects, or .cursor/mcp.json for one project:

{
"mcpServers": {
"unifi": {
"url": "http://<docker-host>:8080/mcp",
"headers": { "Authorization": "Bearer <token>" }
}
}
}

Add to ~/.codex/config.toml:

[mcp_servers.unifi]
url = "http://<docker-host>:8080/mcp"
bearer_token_env_var = "UNIFI_MCP_TOKEN"

Then export UNIFI_MCP_TOKEN=<token> before running codex.

Any client that supports MCP Streamable HTTP works. Point it at http://<docker-host>:8080/mcp and send the bearer token header.

If your client only supports stdio, you have two options. You can use stdio mode, or you can keep the shared HTTP server and connect through a stdio-to-HTTP bridge such as mcp-remote:

{
"command": "npx",
"args": ["-y", "mcp-remote", "http://<docker-host>:8080/mcp", "--header", "Authorization: Bearer <token>"]
}

In stdio mode the MCP client runs the container itself and talks to it over stdin/stdout. No port is opened, and no MCP_AUTH_TOKEN is needed because only the client can reach the server.

The general shape is:

Terminal window
docker run -i --rm \
-e MCP_TRANSPORT=stdio \
-e UNIFI_URL=https://192.168.1.1 \
-e UNIFI_API_KEY=your-api-key \
ghcr.io/mattoddie/unifi-mcp:latest

Tips:

  • Keep secrets out of the client config. Pass -e NAME without a value so Docker copies the variable from the client’s environment, as in the Claude Desktop example. You can also use --env-file /path/to/unifi.env.
  • Always pass -i and never -t. A TTY corrupts the MCP message stream.
  • Docker on another machine works too. Set DOCKER_HOST in the client’s env, and note that UNIFI_URL must be reachable from that machine.
  • Pin a version (for example :1.2.3) so a new latest doesn’t surprise you. See Deployment.