Loading repository data…
mozhaa / repository
An MCP server for executing commands in a persistent sbt shell session
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
An MCP server for executing commands in a persistent sbt shell session.
pip install mcp-sbt-shell
Start the server with default settings:
mcp_sbt_shell
--sbt-executable: sbt executable path (default: sbt.bat)--cwd: Working directory (default: current directory)--port: Server port (default: 8080)--timeout: Command timeout in seconds (default: 30)sbt_executeExecute commands in a persistent sbt shell session. This tool maintains a long-running sbt process to avoid startup overhead and provides direct access to sbt's build capabilities.
Parameters:
command (string) - Required. The sbt command to execute (e.g., "compile", "test", "run")Returns:
output (string) - The complete output from the sbt command execution, including any compilation messages, test results, or error information.The tool will execute the command in the configured sbt session and return the full output, making it suitable for compiling code, running tests, packaging applications, or any other sbt task supported by your project's build configuration.
It sends command to sbt shell, then waits for byte sequence (\x1b\x5b\x3f\x32\x30\x30\x34\x68\x3e\x2e\x2e\x2e\x2e) that signals the end of command execution (tested on Windows with sbt.bat).
build.sbt in the working directorySelected from shared topics, language and repository description—not editorial ratings.
elusznik /
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
81/100 healthbrycewang-stanford /
StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills, an MCP server, and R/Stata parity validation.
81/100 healthbazinga012 /
The MCP Code Executor is an MCP server that allows LLMs to execute Python code within a specified Conda environment.
77/100 healthfkiene /
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
82/100 healthpaiml /
Pragmatic AI Labs MCP Agent Toolkit - An MCP Server designed to make code with agents more deterministic
78/100 healthran-isenberg /
This repository provides a working, deployable, open source-based, serverless MCP server blueprint with an AWS Lambda function and AWS CDK Python code with all the best practices and a complete CI/CD pipeline.
77/100 health