The Babashka MCP Server allows interaction with the Babashka interpreter via the Model Context Protocol (MCP), enabling code execution and resource management.
Execute Babashka code: Run Clojure scripts and expressions through the server with configurable timeouts.
Timeout configuration: Set execution timeouts between 1-300 seconds (1,000-300,000 milliseconds), with a default of 30 seconds.
Access command history: Retrieve and browse results of recent command executions through MCP resources (e.g., babashka://commands/{index}).
Result caching: Automatically cache recent command executions for efficient retrieval.
Custom configuration: Specify the path to the Babashka executable using the BABASHKA_PATH environment variable.
Development roadmap: Future plans include self-hosting, REPL integration, and performance optimizations.
The MCP server provides integration with Babashka, which is a native Clojure interpreter for scripting. It allows execution of Clojure code through the MCP protocol.
The README mentions GitHub Actions tools for Babashka, including setup-babashka and babashka-docker-action, which are recommended for using Babashka in GitHub Actions workflows.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Babashka MCP Server execute (+ 1 2 3) to test basic arithmetic"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server for interacting with Babashka, a native Clojure interpreter for scripting.
Execute Babashka code through MCP tools
Cache recent command results
Access command history through MCP resources
Configurable command timeouts
Related MCP server: Claude Code Control MCP
Babashka can be installed in several ways:
brew install borkdude/brew/babashkabash < <(curl -s https://raw.githubusercontent.com/babashka/babashka/master/install)# Using scoop
scoop install babashkaFor other installation methods, see the official Babashka installation guide.
After installation, verify Babashka works:
# Check version
bb --version
# Try a simple expression
bb -e '(+ 1 2 3)'
# Run a script from string
bb -e '(defn hello [x] (str "Hello, " x "!")) (hello "World")'
# Use -i flag to process lines of input
ls | bb -i '(take 2 *input*)'# Install dependencies
npm install
# Build the MCP server
npm run buildThe server can be configured through environment variables:
BABASHKA_PATH: Path to the Babashka executable (default: "bb")
Execute Babashka code with optional timeout:
{
name: "execute",
arguments: {
code: string; // Babashka code to execute
timeout?: number; // Timeout in milliseconds (default: 30000)
}
}Example:
{
name: "execute",
arguments: {
code: "(+ 1 2 3)",
timeout: 5000
}
}The server maintains a cache of recent command executions accessible through:
babashka://commands/{index} - Access specific command results by index
Babashka supports explicit tail call optimization through the recur special form, but does not implement automatic TCO. For example:
;; This will cause stack overflow
(defn countdown [n]
(if (zero? n)
:done
(countdown (dec n))))
;; This works with TCO using recur
(defn countdown [n]
(if (zero? n)
:done
(recur (dec n))))Babashka GitHub Repository - The main Babashka project
Babashka Book - Official documentation
Babashka Examples - Collection of example scripts
pod-babashka-buddy - Cryptographic API for Babashka
bb-clis - Collection of useful Babashka CLI scripts
bb-scripts - Various utility scripts for Babashka
setup-babashka - GitHub Actions for installing Babashka
babashka-docker-action - Run Babashka scripts in GitHub Actions
This server is designed to eventually become self-hosting, meaning it will be rewritten in Babashka itself. The current TypeScript implementation serves as a reference and starting point.
Self-Hosted Implementation
Rewrite the MCP server in Babashka
Leverage Babashka's native capabilities for better performance
Remove Node.js dependency
Maintain full compatibility with MCP protocol
Support all current features:
Command execution
Resource management
Command history
Timeout handling
Enhanced Features
Add support for Babashka pods
Implement file watching capabilities
Add REPL integration
Support for multiple Babashka instances
Performance Optimizations
Implement caching strategies
Optimize resource usage
Reduce startup time
Testing & Documentation
Comprehensive test suite
API documentation
Usage examples
Performance benchmarks
Execute Babashka (bb) code
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | Babashka code to execute | |
| timeout | No | Timeout in milliseconds (default: 30000) |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0executeScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'execute' has a clear and distinct purpose for running Babashka code.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'execute' is straightforward and appropriate for its function.
A single tool is too few for most practical server purposes, as it severely limits functionality and flexibility. While it might suffice for a minimal interface, it feels thin and under-scoped for general use.
The tool provides basic execution capability, but there are notable gaps such as no tools for managing scripts, handling dependencies, or providing utilities like linting or debugging. This limits the server's usefulness for broader Babashka workflows.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
A Model Context Protocol server for Wix AI tools
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
