Heroku MCP Code Execution - Go

• Heroku MCP Code Execution - Go
  • Automatic Deployment
  • Manual Deployment
    • Set Required Environment Variables from Heroku CLI
  • Local Testing
    • Local SSE
      • Local SSE - Example Requests
    • Local STDIO
      • 1. Local STDIO - Example Go STDIO Client
      • 2. Local STDIO - Direct Calls
  • Remote Testing
    • Remote SSE
    • Remote STDIO
      • 1. Remote STDIO - Example Go STDIO Client, Running On-Server
      • 2. Remote STDIO - Direct Calls to One-Off Dyno
    • 3. Coming Soon - Heroku MCP Gateway!

Automatic Deployment

Manual Deployment

Set Required Environment Variables from Heroku CLI

Instead of manually setting each variable, use the Heroku CLI to pull the correct values.

export APP_NAME=<your-heroku-app-name>
heroku create $APP_NAME

heroku buildpacks:add --index 1 heroku-community/apt -a $APP_NAME
heroku buildpacks:add --index 2 heroku/python -a $APP_NAME
# set a private API key that you create, for example:
heroku config:set API_KEY=$(openssl rand -hex 32) -a $APP_NAME
heroku config:set STDIO_MODE_ONLY=<true/false> -a $APP_NAME

Note: we recommend setting STDIO_MODE_ONLY to true for security and code execution isolation security in non-dev environments.

If you only want local & deployed STDIO capabilities (no SSE server), run:

heroku ps:scale web=0 -a $APP_NAME

If you do want a deployed SSE server, run:

heroku ps:scale web=1 -a $APP_NAME
heroku config:set WEB_CONCURRENCY=1 -a $APP_NAME

Optionally, put these config variables into a local .env file for local development:

heroku config -a $APP_NAME --shell | tee .env > /dev/null

Next, connect your app to your git repo:

heroku git:remote -a $APP_NAME

And deploy!

git push heroku main

View logs with:

heroku logs --tail -a $APP_NAME

Local Testing

Local SSE

One-time packages installation:

virtualenv venv
source venv/bin/activate
pip install -r requirements.txt

If you're testing SSE, in one terminal pane you'll need to start the server:

source venv/bin/activate
export API_KEY=$(heroku config:get API_KEY -a $APP_NAME)
uvicorn src.sse_server:app --reload

Running with --reload is optional, but great for local development

Next, in a new pane, you can try running some queries against your server:

Local SSE - Example Requests

First run:

export API_KEY=$(heroku config:get API_KEY -a $APP_NAME)

List tools:

python example_clients/test_sse.py mcp list_tools | jq

Example tool call request: NOTE: this will intentionally NOT work if you have set STDIO_MODE_ONLY to true.

python example_clients/test_stdio.py mcp call_tool --args '{
  "name": "code_exec_go",
  "arguments": {
    "code": "package main\nimport (\n  \"github.com/fatih/color\"\n)\nfunc main() {\n  color.NoColor = false\n  color.Red(\"This should be red!\")\n}",
    "packages": ["github.com/fatih/color"]
  }
}' | jq -r '.content[0].text' | jq -r .stdout

Local STDIO

There are two ways to easily test out your MCP server in STDIO mode:

1. Local STDIO - Example Go STDIO Client

List tools:

python example_clients/test_stdio.py mcp list_tools | jq

Example tool call request:

python example_clients/test_stdio.py mcp call_tool --args '{
  "name": "code_exec_go",
  "arguments": {
    "code": "package main\nimport (\n  \"fmt\"\n  \"math/rand\"\n)\nfunc main() {\n  for i := 0; i < 50; i++ {\n    fmt.Printf(\"%f \", rand.Float64())\n  }\n}",
    "packages": []
  }
}' | jq

2. Local STDIO - Direct Calls

Example tool call request:

cat <<EOF | python -m src.stdio_server

{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"0.1.0","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}

{"jsonrpc":"2.0","method":"notifications/initialized","params":{}}

{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"code_exec_go","arguments":{"code":"package main\nimport (\n  \"fmt\"\n  \"math/rand\"\n)\nfunc main() {\n  for i := 0; i < 50; i++ {\n    fmt.Printf(\"%f \", rand.Float64())\n  }\n}","packages":[]}}}
EOF

(Note that the server expects the client to send a shutdown request, so you can stop the connection with CTRL-C)

Remote Testing

export API_KEY=$(heroku config:get API_KEY -a $APP_NAME)
export MCP_SERVER_URL=$(heroku info -s -a $APP_NAME | grep web_url | cut -d= -f2)

Remote SSE

To test your remote SSE server, you'll need to make sure a web process is actually spun up. To save on costs, by default this repository doesn't spin up web dynos on creation, as many folks only want to use STDIO mode (local and one-off dyno) requests:

heroku ps:scale web=1 -a $APP_NAME

You only need to do this once, unless you spin back down to 0 web dynos to save on costs (heroku ps:scale web=0 -a $APP_NAME). To confirm currently running dynos, use heroku ps -a $APP_NAME.

Next, you can run the same queries as shown in the Local SSE - Example Requests testing section - because you've set MCP_SERVER_URL, the client will call out to your deployed server.

Remote STDIO

There are two ways to test out your remote MCP server in STDIO mode:

1. Remote STDIO - Example Go STDIO Client, Running On-Server

To run against your deployed code, you can run the example client code on your deployed server inside a one-off dyno:

heroku run --app $APP_NAME -- bash -c 'python -m example_clients.test_stdio mcp list_tools | jq'

or:

heroku run --app "$APP_NAME" -- bash <<'EOF'
python -m example_clients.test_stdio mcp call_tool --args '{
  "name": "code_exec_go",
  "arguments": {
    "code": "package main\nimport (\n  \"fmt\"\n  \"math/rand\"\n)\nfunc main() {\n  for i := 0; i < 50; i++ {\n    fmt.Printf(\"%f \", rand.Float64())\n  }\n}",
    "packages": []
  }
}' | jq
EOF

2. Remote STDIO - Direct Calls to One-Off Dyno

Or, you can also run or simulate a client locally that sends your client-side requests to a one-off dyno:

heroku run --app "$APP_NAME" -- bash -c "python -m src.stdio_server 2> logs.txt" <<EOF

{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"0.1.0","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}

{"jsonrpc":"2.0","method":"notifications/initialized","params":{}}

{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"code_exec_go","arguments":{"code":"package main\nimport (\n  \"fmt\"\n  \"math/rand\"\n)\nfunc main() {\n  for i := 0; i < 50; i++ {\n    fmt.Printf(\"%f \", rand.Float64())\n  }\n}","packages":[]}}}
EOF

Again, note that since we're running our request through a single command, we're unable to simulate a client's shutdown request.

3. Coming Soon - Heroku MCP Gateway!

Soon, you'll also be able to connect up your MCP repo to Heroku's MCP Gateway, which will make streaming requests and responses from one-off MCP dynos simple!

The Heroku MCP Gateway implements a rendezvous protocol so that you can easily talk to your MCP server one-off dynos (code execution isolation!) with seamless back-and-forth communication.

After deploying and registering your MCP app on heroku, requests made to Heroku's v1/mcp/servers will show you your registered MCP tools, and requests made to v1/agents/heroku will be able to execute your MCP tools automatically via one-off dynos.