-
security-
license-
qualityAn MCP server that analyzes codebases and generates contextual prompts, making it easier for AI assistants to understand and work with code repositories.
Last updated -
14
MIT License
The Rules MCP Server provides coding agents with on-demand access to context-specific rules and best practices, primarily for tasks like writing tests.
Fetch Task-Specific Rules: Access guidelines for writing tests, authoring UI, or reviewing PRs.
Language-Specific Support: Currently supports Python and TypeScript with dedicated rules for each.
Contextual Delivery: Rules are dynamically fetched based on relevance to the current task, reducing distractions.
Tool Integration: Works seamlessly with Claude Code, Cursor, and Claude Desktop.
Centralized Best Practices: Eliminates the need for manually managing coding guidelines across different projects or IDEs.
Supports deployment of the MCP server on Netlify's platform, enabling hosting of rules and guidelines.
My Rules
An MCP server for all my rules, prompts, etc etc. Allows agents to call rules on demand.
There's no point filling 4 paragraphs of instructions for how to write tests if your current session isn't going to write a test.
Spiritually similar to Cursor's rules.
Usage
Claude Code
claude mcp add --transport http rules https://mcp.cianfrani.dev/mcp
Cursor
Claude Desktop
{
"rules": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.cianfrani.dev/mcp"
]
}
}
What's It Do?
Allows coding agents to lookup rules on demand within the context of their current task.
> write a test for @calc.py
⎿ Read calc.py (26 lines)
⏺ rules:get_rules_for_writing_tests (MCP)(language: "python")
⎿ - Before testing a protected method, ask "Can this logic be adequately tested through the public interface?". If yes, don't test the protected method directly.
If no, continue testing the protected method.
- Remember to write tests using the Arrange, Act, Assert pattern.
… +12 lines (ctrl+r to expand)
⏺ Write(test_calc.py)
Why?
It's really annoying trying to carry all these little notes between projects/IDEs.
I don't want to have to manually invoke rules.
How's It Work?
Clearly-defined tool descriptions allow the agent to fetch rules on demand, only if they appear to be relevant.
What Doesn't work?
Patterns must be associated with a specific action. For example, "writing tests", "authoring UI", "reviewing a PR".
The agent ultimately decides if it's going to call the tool. Sometimes it does. Sometimes it doesn't.
Tools
get_rules_for_writing_testsUse when: writing any type of test,
Inputs:
language(string)
get_rules_for_composing_ui
Use when: creating new frontend components
Prompts
In Claude Code, invoke prompts as slash commands.
pr-review
Use when: you want feedback on a unit of work
/pr-review
See resources/pr-review.md for the full template.
Resources
Dev
Start the server
npm run dev
Open MCP inspector
npm run inspect
Related MCP Servers
- -security-license-qualityModel Context Protocol (MCP) server that provides AI assistants with advanced web research capabilities, including Google search integration, intelligent content extraction, and multi-source synthesis.Last updated -114MIT License
- AsecurityFlicenseAqualityAn MCP server that enhances AI agents' coding capabilities by providing zero hallucinations, improved code quality, security-first approach, high test coverage, and efficient context management.Last updated -15381
- AsecurityAlicenseAqualityA comprehensive MCP server providing tools for AI agents to interact with code, including reading symbols, importing modules, replacing text, and sending OS notifications.Last updated -3227MIT License