emcee

emcee

emcee is a tool that provides a Model Context Protocol (MCP) server
for any web application with an OpenAPI specification.
You can use emcee to connect Claude Desktop and other apps
to external tools and data services,
similar to ChatGPT plugins.

Quickstart

If you're on macOS and have Homebrew installed,
you can get up-and-running quickly.

# Install emcee
brew install mattt/tap/emcee

Make sure you have Claude Desktop installed.

To configure Claude Desktop for use with emcee:

1. Open Claude Desktop Settings (⌘,)
2. Select the "Developer" section in the sidebar
3. Click "Edit Config" to open the configuration file

The configuration file should be located in the Application Support directory.
You can also open it directly in VSCode using:

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

Add the following configuration to add the weather.gov MCP server:

{
  "mcpServers": {
    "weather": {
      "command": "emcee",
      "args": ["https://api.weather.gov/openapi.json"]
    }
  }
}

After saving the file, quit and re-open Claude.
You should now see 🔨57 in the bottom right corner of your chat box.
Click on that to see a list of all the tools made available to Claude through MCP.

Start a new chat and ask it about the weather where you are.

What's the weather in Portland, OR?

Claude will consult the tools made available to it through MCP
and request to use one if deemed to be suitable for answering your question.
You can review this request and either approve or deny it.

If you allow, Claude will communicate with the MCP
and use the result to inform its response.

Why use emcee?

MCP provides a standardized way to connect AI models to tools and data sources.
It's still early days, but there are already a variety of available servers
for connecting to browsers, developer tools, and other systems.

We think emcee is a convenient way to connect to services
that don't have an existing MCP server implementation —
especially for services you're building yourself.
Got a web app with an OpenAPI spec?
You might be surprised how far you can get
without a dashboard or client library.

Installation

Installer Script

Use the installer script to download and install a
pre-built release of emcee for your platform
(Linux x86-64/i386/arm64 and macOS Intel/Apple Silicon).

# fish
sh (curl -fsSL https://get.emcee.sh | psub)

# bash, zsh
sh <(curl -fsSL https://get.emcee.sh)

Homebrew

Install emcee using Homebrew.

brew install mattt/tap/emcee

Docker

Prebuilt Docker images with emcee are available.

docker run -it ghcr.io/mattt/emcee

Build From Source

Requires go 1.24 or later.

git clone https://github.com/mattt/emcee.git
cd emcee
go build -o emcee cmd/emcee/main.go

Once built, you can run in place (./emcee)
or move it somewhere in your PATH, like /usr/local/bin.

Usage

Usage:
  emcee [spec-path-or-url] [flags]

Flags:
      --basic-auth string    Basic auth value (either user:pass or base64 encoded, will be prefixed with 'Basic ')
      --bearer-auth string   Bearer token value (will be prefixed with 'Bearer ')
  -h, --help                 help for emcee
      --raw-auth string      Raw value for Authorization header
      --retries int          Maximum number of retries for failed requests (default 3)
  -r, --rps int              Maximum requests per second (0 for no limit)
  -s, --silent               Disable all logging
      --timeout duration     HTTP request timeout (default 1m0s)
  -v, --verbose              Enable debug level logging to stderr
      --version              version for emcee

emcee implements Standard Input/Output (stdio) transport for MCP,
which uses JSON-RPC 2.0 as its wire format.

When you run emcee from the command-line,
it starts a program that listens on stdin,
outputs to stdout,
and logs to stderr.

Authentication

For APIs that require authentication,
emcee supports several authentication methods:

These authentication values can be provided directly
or as 1Password secret references.

When using 1Password references:

• Use the format op://vault/item/field
  (e.g. --bearer-auth="op://Shared/X/credential")
• Ensure the 1Password CLI (op) is installed and available in your PATH
• Sign in to 1Password before running emcee or launching Claude Desktop

# Install op
brew install 1password-cli

# Sign in 1Password CLI
op signin

{
  "mcpServers": {
    "twitter": {
      "command": "emcee",
      "args": [
        "--bearer-auth=op://shared/x/credential",
        "https://api.twitter.com/2/openapi.json"
      ]
    }
  }
}

[!IMPORTANT]
emcee doesn't use auth credentials when downloading
OpenAPI specifications from URLs provided as command arguments.
If your OpenAPI specification requires authentication to access,
first download it to a local file using your preferred HTTP client,
then provide the local file path to emcee.

Transforming OpenAPI Specifications

You can transform OpenAPI specifications before passing them to emcee using standard Unix utilities. This is useful for:

• Selecting specific endpoints to expose as tools
  with jq or yq
• Modifying descriptions or parameters
  with OpenAPI Overlays
• Combining multiple specifications
  with Redocly

For example,
you can use jq to include only the point tool from weather.gov.

cat path/to/openapi.json | \
  jq 'if .paths then .paths |= with_entries(select(.key == "/points/{point}")) else . end' | \
  emcee

JSON-RPC

You can interact directly with the provided MCP server
by sending JSON-RPC requests.

[!NOTE]
emcee provides only MCP tool capabilities.
Other features like resources, prompts, and sampling aren't yet supported.

List Tools

{ "jsonrpc": "2.0", "method": "tools/list", "params": {}, "id": 1 }

{
  "jsonrpc": "2.0",
  "result": {
    "tools": [
      // ...
      {
        "name": "tafs",
        "description": "Returns Terminal Aerodrome Forecasts for the specified airport station.",
        "inputSchema": {
          "type": "object",
          "properties": {
            "stationId": {
              "description": "Observation station ID",
              "type": "string"
            }
          },
          "required": ["stationId"]
        }
      }
      // ...
    ]
  },
  "id": 1
}

Call Tool

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": { "name": "taf", "arguments": { "stationId": "KPDX" } },
  "id": 1
}

{
  "jsonrpc":"2.0",
  "content": [
    {
      "type": "text",
      "text": /* Weather forecast in GeoJSON format */,
      "annotations": {
        "audience": ["assistant"]
      }
    }
  ]
  "id": 1
}

Debugging

The MCP Inspector is a tool for testing and debugging MCP servers.
If Claude and/or emcee aren't working as expected,
the inspector can help you understand what's happening.

npx @modelcontextprotocol/inspector emcee https://api.weather.gov/openapi.json
# 🔍 MCP Inspector is up and running at http://localhost:5173 🚀

open http://localhost:5173

License

This project is available under the MIT license.
See the LICENSE file for more info.