MemorizedMCP / rules
Cursor rule8 starsChanged 14 months agoMITView on GitHub
Using Context7
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,183 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
The file
We split this context7-mcp-tools-instructions.mdc into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
When activated, you have access to the following internal tools to fulfill the user's request.
- Distinctive: line 21
When to Use: Use this first to ensure you are requesting docs for the correct library.
- Very specific: line 28
When to Use: After you have used resolve-library-id or if the user provides an exact Context7-compatible ID.
- Very specific: line 40
Use the resolve-library-id tool to get the precise library ID.
- Very specific: line 41
Use the get-library-docs tool with the ID to fetch the relevant documentation.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
--- description: Using Context7 globs: alwaysApply: true --- # AI Agent Rule: Using Context7 **Objective:** To provide accurate, up-to-date, and version-specific code documentation and examples by using the Context7 MCP server. **Core Principle:** When a prompt involves a request for code, examples, or information about a software library, you should use the Context7 tool to fetch the latest documentation directly from the source. This prevents the use of outdated training data and avoids generating hallucinated or non-existent APIs. ## **Available Tools & Commands** When activated, you have access to the following internal tools to fulfill the user's request. You should use these tools logically to first identify the correct library and then retrieve its documentation. **1. `resolve-library-id`** * **Purpose:** Resolves a general library name (e.g., "next.js", "mongo") into a specific, Context7-compatible library ID. * **When to Use:** Use this first to ensure you are requesting docs for the correct library. * **Parameters:** * `libraryName` (required): The name of the library you are searching for. **2. `get-library-docs`** * **Purpose:** Fetches the documentation for a library once you have its specific ID. * **When to Use:** After you have used `resolve-library-id` or if the user provides an exact Context7-compatible ID. * **Parameters:** * `context7CompatibleLibraryID` (required): The exact ID for the library (e.g., `/vercel/next.js`, `/mongodb/docs`). * `topic` (optional): A specific topic to focus on within the documentation (e.g., "routing", "hooks"). * `tokens` (optional, default: 10000): The maximum number of tokens to return in the documentation. --- ## **Workflow** 1. Think if Context7 is needed, if yes use it if no dont. 2. Identify the library or package the user is asking about. 3. Use the `resolve-library-id` tool to get the precise library ID. 4. Use the `get-library-docs` tool with the ID to fetch the relevant documentation. If the user mentioned a specific topic, include it in the `topic` parameter. 5. Synthesize the retrieved documentation and code examples into a final, accurate answer for the user.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.