mcpField
L
Labby

Labby

Local
github.comDeveloper Tools9Updated 1d ago
RepositoryVisit website

About Labby

Labby is a Rust MCP gateway and operations tool for people who connect and manage MCP services. It combines gateway routing, authentication, Code Mode, a CLI, and a web operator interface, alongside proxying, logs, and host setup.

Key features

  1. 01Connect HTTP and stdio upstream MCP servers
  2. 02Filter and publish protected MCP routes
  3. 03Search and execute tools through Code Mode
  4. 04Provide authentication, CLI, HTTP API, and web UI
  5. 05Support setup checks, file operations, and log inspection

Use cases

  1. 01Aggregate upstream MCP servers and filter their exposure
  2. 02Configure authentication and access for MCP routes
  3. 03Run reusable JavaScript snippets through Code Mode
  4. 04Check gateway health and inspect server logs

MCP support

Labby connects to HTTP and stdio upstream MCP servers, inspects their tools, resources, and prompts, then filters and publishes protected MCP routes. It can also condense an upstream catalog into Code Mode search and execute.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ai-dinglebear-labby": {
      "command": "npx",
      "args": [
        "-y",
        "@dinglebear/labby"
      ],
      "env": {
        "LABBY_VERSION": "<LABBY_VERSION>",
        "LABBY_REPO": "<LABBY_REPO>",
        "LABBY_LOG": "<LABBY_LOG>"
      }
    }
  }
}
Run commandnpx -y @dinglebear/labby
Environment variables to set
LABBY_VERSIONOptional GitHub release tag override for the downloaded Labby binary.
LABBY_REPOOptional GitHub owner/repo override for release asset downloads.
LABBY_LOGTracing filter for Labby runtime logs.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@dinglebear/labby2.6.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.