AGENTS.md
This MCP server provides project management and AI-powered task automation through a web-based interface with SQLite storage, user authentication, and version control capabilities. Built by Benhao Tang with Express.js and Next.js, it integrates multiple AI providers (OpenAI, Google Gemini, Groq) and MCP tool servers to enable automated task execution through 'subagents' that can perform web searches, code execution, and file operations within project contexts. The implementation features hierarchical task management with drag-and-drop Kanban boards, markdown-based agent configuration, scratchpad systems for iterative work, project sharing with granular permissions, and Docker deployment support. Designed for teams and individuals who need AI-assisted project workflows with persistent state management, collaborative editing, and automated task delegation to specialized AI agents with access to external tools and data sources.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/benhaotang/mcp-http-agent-md
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve AGENTS.md from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.