Build-Scout

A comprehensive Model Context Protocol (MCP) server that enables LLM clients to interact with various build systems including Gradle, Maven, NPM/Yarn, Cargo, Python, Makefile, and CMake.

Build-scout provides a standardized interface for build tool operations through the Model Context Protocol, allowing AI assistants to understand, analyze, and manipulate software projects across multiple build technologies.

- Gradle(Groovy and Kotlin DSL) -build.gradle,build.gradle.kts
- Maven-pom.xml
- NPM/Yarn-package.json
- Cargo(Rust) -Cargo.toml
- Python-requirements.txt,setup.py
- Makefile-Makefile
- CMake-CMakeLists.txt

- find_build_system- Discovers build systems in project directories
- build_system_file_paths- Returns paths to build system files

- build_gradle_project- Executes Gradle builds with optional checks
- gradle_tester- Runs Gradle build and test tasks

- dependencies_list- Lists all top-level dependencies with versions
- update_dependency_version- Updates dependency versions in build files
- latest_dependency_version- Fetches latest versions from repositories

- find_class_usage- Finds class usage across the codebase
- jar_diff_reporter- Compares JAR files for differences

- get_file_info- Retrieves file metadata and information
- get_resource_info- Gets resource information
- replace_source_code_complete- Performs source code replacements

- download_current_latest_source- Downloads latest source versions

This will increment the version number and build the JAR:

./gradlew clean prebuild updateConfigJson

Completed and tested all the tools, prompt and root to see the native image working. Still need to review more for edge cases but try it out.

To run the server locally and get out put for native image class discovery.

"scout-server": { "command": "java", "args": [ "-agentlib:native-image-agent=config-output-dir=/Users/davidparry/code/github/mcp-servers/build-scout/tmp/META-INF/native-image", "-Dorg.gradle.native=false", "-Djava.awt.headless=true", "-jar /Users/davidparry/code/github/mcp-servers/build-scout/build/libs/scout-1.0.105.jar" ], "env": { "BUILD_SCOUT_LOGGING": "DEBUG" } }

After running the server, you can generate the native image configuration files will append to the files already in the src/main/resources/META-INF/native-image directory.:

$GRAALVM_HOME/bin/native-image-configure generate --input-dir=tmp/META-INF/native-image --output-dir=src/main/resources/META-INF/native-image

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "scout-server": { "command": "java", "args": ["-jar", "/path/to/scout-1.0.{VERSION}.jar"] } } }

{ "mcpServers": { "scout-server": { "command": "scout", "args": [], "env": { "BUILD_SCOUT_LOGGING": "ERROR" } } } }

Add to your~/.config/github-copilot/intellij/mcp.json:

{ "servers": { "scout-server": { "command": "java", "args": ["-jar", "/path/to/scout-1.0.{VERSION}.jar"] } } }

The server can be integrated with any MCP-compatible client by configuring the appropriate JSON configuration file.

{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "find_build_system", "arguments": { "project_root": "/path/to/your/project" } } }

{ "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "build_gradle_project", "arguments": { "project_root": "/path/to/gradle/project", "check": true } } }

{ "jsonrpc": "2.0", "id": 3, "method": "tools/call", "params": { "name": "dependencies_list", "arguments": { "path": "/path/to/build.gradle" } } }

{ "jsonrpc": "2.0", "id": 4, "method": "tools/call", "params": { "name": "update_dependency_version", "arguments": { "groupId": "org.springframework.boot", "artifactId": "spring-boot-starter-web", "version": "3.2.0", "path": "/path/to/build.gradle" } } }

- Main.java- Entry point and server initialization
- RequestController- Routes JSON-RPC requests to appropriate handlers
- SchemaInitializer- Registers tools and handlers using annotations
- IOHandler- Manages input/output communication
- BuildSystem- Core interface for build system operations

- Annotation-based tool registration using@Schemaannotations
- Virtual thread processing for concurrent request handling
- Gradle Tooling API integration for direct Gradle operations
- Native image support with GraalVM configuration
- Automatic version management and JAR updates

src/ ├── main/ │ ├── java/ │ │ └── com/davidparry/scout/ │ │ ├── Main.java │ │ ├── Router.java │ │ ├── tools/ # MCP tools implementation │ │ ├── common/ # Build system implementations │ │ ├── spec/ # MCP protocol specifications │ └── resources/ │ └── META-INF/native-image/ # GraalVM configuration └── test/ └── java/ # Unit tests

- Increments patch version numbers
- Updates JAR references in MCP client configurations
- Generates version metadata for runtime access
- Build failures- Check Java version compatibility (requires Java 21+)
- Native image issues- Ensure GraalVM is properly configured
- Tool registration- Static classes not registered correctly; for the native image.

The server includes comprehensive logging at different levels. Check the console output for detailed information about tool execution and errors.
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Ensure all tests pass
- Submit a pull request

This project is licensed under the MIT License - see the LICENSE file for details.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

All Azure MCP tools in a single server. The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and Azure services. Azure MCP Server can be used alone or with the GitHub Copilot for Azure extension in VS Code.

Flag features, manage company data, and control feature access using Bucket.

Enable AI Agents to fix build failures from CircleCI.

interacts with ConfigCat feature flag platform. Supports managing feature flags, configs, environments, products and organizations. Helps to integrate ConfigCat SDK, implement feature flags or remove zombie (stale) flags.

Boost security in your dev lifecycle via SAST, SCA, Secrets & IaC scanning with Cycode.

Turn your favourite AI tool into a feature management assistant. DevCycle's MCP works with your favourite coding assistant so you can create and monitor feature flags using natural language right in your workflow.

Official Docker MCP Toolkit for discovering, configuring, and running containerized MCP servers through Docker Desktop and the Docker MCP gateway.

The Octopus MCP Server provides your AI assistant with powerful tools that allow it to inspect, query, and diagnose problems within your Octopus instance, transforming it into your ultimate DevOps wingmate.