mcpField
S
Sonar MVP Server

Sonar MVP Server

Local
github.com/lreimerDeveloper Tools2Updated 77w ago
Repository

About Sonar MVP Server

Sonar MVP Server is a Go MCP server for accessing the SonarQube Cloud API. It supports local stdio use and SSE transport, with deployment instructions for Google Cloud Run.

Key features

  1. 01SonarQube Cloud API access
  2. 02stdio and SSE transports
  3. 03Google Cloud Run deployment

Use cases

  1. 01Connecting an MCP client to SonarQube Cloud
  2. 02Running the server locally over stdio
  3. 03Deploying the server to Google Cloud Run

MCP support

It exposes SonarQube Cloud API access through an MCP server. The README shows stdio configuration and SSE usage.

#sonarqube#sonar#mcp-server#mcp-go

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "sonar": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector"
      ]
    }
  }
}
Run commandnpx -y @modelcontextprotocol/inspector

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@modelcontextprotocol/inspector

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

From the project README

Sonar MVP Server

An MCP server implementation for the SonarQube Cloud API in Golang.

Build and Release

# to quickly build the latest snapshot
goreleaser build --snapshot --clean
goreleaser release --skip=publish --snapshot --clean

Usage Instructions

If you want to use the tool locally, e.g. with Claude Desktop, use the following configuration for the MCP server.

{
    "mcpServers": {
      "sonar": {
        "command": "/Users/mario-leander.reimer/Applications/sonar-mcp-server",
        "args": ["-t", "stdio"],
        "env": {
          "SONAR_TOKEN": "<<INSERT TOKEN HERE>>"
        }
      }
    }
}

Alternatively, you can use the MCP introspector for easy local development:

# as stdio binary
npx @modelcontextprotocol/inspector go run main.go

# as SSE server using 
go run main.go --transport sse
npx @modelcontextprotocol/inspector npx mcp-remote@next http://localhost:8080/sse
npx @modelcontextprotocol/inspector

Deployment

Currently using manual Google Cloud Run deployment. Can either be deployed directly from source or using the Docker image built on Github.

# create a new secret for the SONAR_TOKEN
gcloud services enable secretmanager.googleapis.com
print $SONAR_TOKEN | gcloud secrets create sonar-token --data-file=-

# next deploy the local build from source to Cloud Run
gcloud services enable run.googleapis.com cloudbuild.googleapis.com artifactregistry.googleapis.com

gcloud secrets add-iam-policy-binding sonar-token \
  --member=serviceAccount:[email protected] \
  --role=roles/secretmanager.secretAccessor

gcloud run deploy sonar-mcp-server --source=. \
  --region=europe-north1 \
  --port=8080 --allow-unauthenticated \
  --set-secrets=SONAR_TOKEN=sonar-token:latest \
  --set-env-vars=BASE_URL=https://sonar-mcp-server-343509396461.europe-north1.run.app

gcloud run services delete sonar-mcp-server --async --region=europe-north1

Maintainer

M.-Leander Reimer (@lreimer), [email protected]

License

This software is provided under the MIT open source license, read the LICENSE file for details.

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.