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
Connects AI tools (agents, assistants, chatbots) directly to GitHub's platform to enable reading repositories, managing issues and pull requests, analyzing code, and automating workflows through natural language interactions.
code-assistant
Provides a standardized interface for AI coding agents to communicate with code editors (Clients) using JSON-RPC 2.0 over stdio, supporting autonomous code analysis and modification.
responsible-vibe-mcp
Guides AI coding agents through structured engineering workflows and manages long-term project memory and documentation for various development tasks.
Lynkr
An AI-powered orchestration platform enabling autonomous agents to interact with a development workspace, execute code, manage git, perform web searches, and communicate with various Large Language Models (LLMs) via a unified API.