
Rules MCP Server
An MCP server that allows coding agents to look up contextual rules and patterns on demand, providing just-in-time guidance for specific tasks like writing tests or authoring UI.
Tools
get_rules_for_writing_tests
When writing tests, ALWAYS ask this tool for rules on how to write the test first. Then, use the rules to write the test.
README
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.
Resources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.