mcp-tasks
Verified Safeby hugoduncan
Overview
Manages development tasks and workflows for AI agents, providing persistent planning, category-based organization, and Git integration to enhance agent productivity and output quality.
Installation
mcp-tasks-serverEnvironment Variables
- CLAUDE_CODE_REMOTE
- CLAUDE_ENV_FILE
Security Notes
The provided source code is truncated and does not include the core Clojure implementation for the MCP server and CLI, limiting a comprehensive security audit. Visible shell scripts appear to follow safe practices, using standard commands for file operations and git. The `web-session-start` script downloads binaries from GitHub releases, a legitimate but inherent risk when executing downloaded code. Prompt templating uses Selmer, which could introduce Server-Side Template Injection (SSTI) vulnerabilities if user-controlled input is unsafely integrated into template contexts. However, the documentation states that variable substitution is 'used internally', suggesting a controlled environment. Without the full Clojure source code that handles prompt rendering and user input processing, it's not possible to definitively rule out templating or other injection risks, hardcoded secrets, or subtle malicious patterns.
Similar Servers
conductor-tasks
Conductor Tasks is an intelligent assistant for developers, transforming requirements into actionable tasks, generating implementation plans, tracking progress, and accelerating AI-powered development directly within the workflow. It serves as a comprehensive AI co-pilot for the development process.
responsible-vibe-mcp
Guides AI coding agents through structured engineering workflows and manages long-term project memory and documentation for various development tasks.
sudocode
Git-native spec and issue management for AI-assisted software development, enabling agents to track context, manage work items, visualize execution, and automate workflows in a local-first, version-controlled manner.
backlog
Manage project backlog tasks with markdown in Git, facilitating collaboration between AI agents and human developers.