finsliparn
Verified Safeby jgabor
Overview
An iterative coding agent that refines LLM-generated code through test-driven validation and multi-attempt selection using Git worktrees.
Installation
bun run src/mcp/server.tsEnvironment Variables
- FINSLIPARN_DEBUG
- FINSLIPARN_LOG_PATH
- FINSLIPARN_LOG_LEVEL
- FINSLIPARN_HOME
- FINSLIPARN_TEST_COMMAND
- FINSLIPARN_MAX_ITERATIONS
- FINSLIPARN_DASHBOARD_PORT
Security Notes
The server primarily executes local `bun test` and `git` commands. Arguments for these commands are either fixed or constructed internally from session data (UUIDs, iteration numbers), significantly reducing the risk of command injection through user input. File system operations are generally constrained to the `.finsliparn` directory within the project root. No direct 'eval' or similar dangerous functions are observed. The core operation relies on trusted local tools. The security model largely depends on the trustworthiness of the code being iterated on and the environment it runs in. The use of Git worktrees provides isolation for iterations, preventing accidental corruption of the main branch during refinement. There is no indication of hardcoded secrets or arbitrary network exposure beyond the standard Model Context Protocol (MCP) IPC.
Similar Servers
github-mcp-server
The GitHub MCP Server enables AI agents, assistants, and chatbots to interact with GitHub's platform for repository management, issue/PR automation, CI/CD intelligence, code analysis, and team collaboration through natural language.
Lynkr
Lynkr is an AI orchestration layer that acts as an LLM gateway, routing language model requests to various providers (Ollama, Databricks, OpenAI, etc.). It provides an OpenAI-compatible API and enables AI-driven coding tasks via a rich set of tools and a multi-agent framework, with a strong focus on security, performance, and token efficiency. It allows AI agents to interact with a defined workspace (reading/writing files, executing shell commands, performing Git operations) and leverages long-term memory and agent learning to enhance task execution.
code-assistant
Standardizes communication between code editors and AI coding agents, enabling autonomous code analysis and modification via command-line, GUI, or server modes.
responsible-vibe-mcp
Manages conversation state and guides LLM coding agents through structured software development workflows with long-term project memory and multi-agent collaboration.