Agent Rules
Agent Rules MCP server by 4regab that enables AI assistants to fetch coding rules and best practices on-demand from GitHub repositories, eliminating the need for local rule files by providing remote access to development standards. Built with TypeScript and the MCP SDK, the implementation offers two core tools: get_rules for retrieving specific rule domains and list_rules for discovering available domains, with intelligent caching, rate limit handling, and support for multiple file formats including .md, .mdc, .chatmode.md, and .instructions.md files. The server includes fallback mechanisms for unauthenticated GitHub API access, metadata extraction from YAML frontmatter, and can be configured to work with any GitHub repository containing rule collections, making it valuable for development teams maintaining consistent coding standards across projects, AI agents requiring context-specific development guidance, and organizations wanting to centralize and share their coding best practices without manual file management.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- PulseMCP
- Repository
- github.com/4regab/agent-rules-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Agent Rules 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.